© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8209
    Prev
    Next
    INDEX
    Explanations

    localhost

    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
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     મેં
    -0.09
     கண
    -0.09
     деся
    -0.08
     குறிப்ப
    -0.08
     ਮੈਂ
    -0.08
    ();↵//
    -0.08
     குறிப்பிட
    -0.08
    erman
    -0.08
     השבוע
    -0.08
    escape
    -0.08
    POSITIVE LOGITS
     tighter
    0.09
     tight
    0.08
     tightly
    0.08
     prescribe
    0.08
     AH
    0.08
     tightened
    0.08
     Agnes
    0.07
     tightening
    0.07
     local
    0.07
     onsite
    0.07
    Activations Density 0.001%

    No Known Activations