© 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 · 11-RESID-POST-AA · 110587 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
11-RESID-POST-AA
110587

INDEX

Explanations

collaboration and teamwork

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-gpt-oss-20b/resid_post_layer_11/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

explode

-0.08

 먼저

-0.07

 Manip

-0.07

出租

-0.07

idosis

-0.07

_BL

-0.07

 Chunk

-0.07

 splitted

-0.07

软

-0.07

 explode

-0.07

POSITIVE LOGITS

 nawo

0.08

 channels

0.08

.Columns

0.08

 Fiction

0.08

ABC

0.07

 Lorem

0.07

 freuen

0.07

 convergence

0.07

 pati

0.07

 mindfulness

0.07

Activations Density 0.057%

No Known Activations