© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GPT-OSS-20B · 23-RESID-POST-AA · 6347 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
23-RESID-POST-AA
6347

INDEX

Explanations

willingness

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0

Dataset (Dashboard)

Various

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 precisava

-0.08

 Traf

-0.07

 failed

-0.07

-0.07

 certe

-0.07

 Failed

-0.07

berry

-0.07

 debated

-0.07

Adr

-0.07

Unsupported

-0.07

POSITIVE LOGITS

 willingness

0.49

 willing

0.47

 bereid

0.41

 dispuesto

0.38

愿

0.37

 готовы

0.37

 bereit

0.35

 Bereits

0.35

 disposto

0.33

 readiness

0.33

Activations Density 0.114%

No Known Activations