# Concept Steering on AxBench (Held-out)

Source: [Concept Steering on AxBench (Held-out)](<https://www.sota2.com/research/sota/concept-steering-on-axbench-held-out>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-08T09:17:40.819Z

Evaluation of model performance on the Concept Steering task using the held-out set of the AxBench dataset, reporting HMean scores.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Concept Steering |
| Dataset (including any stated split) | AxBench (Held-out) |
| Metric | HMean |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [HMean](<https://www.sota2.com/research/sota/concept-steering-on-axbench-held-out.md?metric=HMean>): Higher is better; unit: SCALAR.

## Recorded results

| Method | HMean | Result date | Report paper |
| --- | --- | --- | --- |
| FLAS | 1.113 | Not recorded | 69fd6e455497b3b670c8960e |
| Prompting | 1.091 | Not recorded | 69fd6e455497b3b670c8960e |
| FLAS | 1.015 | Not recorded | 69fd6e455497b3b670c8960e |
| HyperSteer | 0.934 | Not recorded | 69fd6e455497b3b670c8960e |
| Prompting | 0.762 | Not recorded | 69fd6e455497b3b670c8960e |
| HyperSteer | 0.608 | Not recorded | 69fd6e455497b3b670c8960e |

### FLAS

HMean: 1.113. Result ID: 69fda98e47f34ce924e0e39c.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e455497b3b670c8960e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e455497b3b670c8960e.md>)

Recorded evaluation configuration: {"Base Model":"Gemma-2-9B-IT","Intervention Layer":"Layer 20","T":"2"}. This record does not assert independent reproduction.

### Prompting

HMean: 1.091. Result ID: 69fda98e47f34ce924e0e39a.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e455497b3b670c8960e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d18.md>)

Recorded evaluation configuration: {"Base Model":"Gemma-2-9B-IT","Intervention Layer":"Layer 20"}. This record does not assert independent reproduction.

### FLAS

HMean: 1.015. Result ID: 69fda98e47f34ce924e0e399.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e455497b3b670c8960e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e455497b3b670c8960e.md>)

Recorded evaluation configuration: {"Base Model":"Gemma-2-2B-IT","Intervention Layer":"Layer 20","T":"2"}. This record does not assert independent reproduction.

### HyperSteer

HMean: 0.934. Result ID: 69fda98e47f34ce924e0e39b.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e455497b3b670c8960e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79111e209131cea7bf3d.md>)

Recorded evaluation configuration: {"Base Model":"Gemma-2-9B-IT","Intervention Layer":"Layer 20"}. This record does not assert independent reproduction.

### Prompting

HMean: 0.762. Result ID: 69fda98e47f34ce924e0e397.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e455497b3b670c8960e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d18.md>)

Recorded evaluation configuration: {"Base Model":"Gemma-2-2B-IT","Intervention Layer":"Layer 20"}. This record does not assert independent reproduction.

### HyperSteer

HMean: 0.608. Result ID: 69fda98e47f34ce924e0e398.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e455497b3b670c8960e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79111e209131cea7bf3d.md>)

Recorded evaluation configuration: {"Base Model":"Gemma-2-2B-IT","Intervention Layer":"Layer 20"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.