© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GPT-OSS-20B · 19-RESID-POST-AA · 18412 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
19-RESID-POST-AA
18412

INDEX

Explanations

brackets, plus signs

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_19/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

非

-0.08

 decisive

-0.08

 независимо

-0.08

 центре

-0.07

ляться

-0.07

алады

-0.07

 leves

-0.07

 ғана

-0.07

.SUCCESS

-0.07

 šte

-0.07

POSITIVE LOGITS

 отсутств

0.16

missing

0.15

 missing

0.15

_missing

0.15

 absent

0.15

 Missing

0.15

Missing

0.15

 ontbre

0.14

缺

0.13

 ausência

0.13

Activations Density 0.011%

No Known Activations