© 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. 95202
    Prev
    Next
    INDEX
    Explanations

    prime

    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
     fou
    -0.08
     flaw
    -0.08
     JB
    -0.08
     CWE
    -0.07
     Aa
    -0.07
     tarn
    -0.07
     Ford
    -0.07
     Entsche
    -0.07
     abat
    -0.07
     cobran
    -0.07
    POSITIVE LOGITS
     команд
    0.08
    .gov
    0.08
     Keywords
    0.07
    Keywords
    0.07
     storia
    0.07
     Constantine
    0.07
     gastronom
    0.07
    (role
    0.07
    KN
    0.07
     국민
    0.07
    Activations Density 0.008%

    No Known Activations