© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GPT-OSS-20B · 3-RESID-POST-AA · 2852 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
3-RESID-POST-AA
2852

INDEX

Explanations

Personality Type/Type

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-gpt-oss-20b/resid_post_layer_3/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

 integrity

-0.08

 Chest

-0.07

וכל

-0.07

 engraved

-0.07

 Registry

-0.07

 registry

-0.07

DHS

-0.07

†

-0.07

 رمز

-0.07

-integr

-0.07

POSITIVE LOGITS

Meeting

0.09

Teen

0.09

Tournament

0.08

 neurotrans

0.08

辅

0.08

 terci

0.08

Rating

0.08

 operative

0.08

 teenager

0.08

meeting

0.07

Activations Density 0.007%

No Known Activations