© 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. 24651
    Prev
    Next
    INDEX
    Explanations

    Movie and book titles

    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
     AH
    -0.08
     DH
    -0.08
     সন্তান
    -0.08
     ಮಕ್ಕಳ
    -0.08
     демократ
    -0.07
     boolean
    -0.07
    .Xml
    -0.07
    LH
    -0.07
     hh
    -0.07
    лод
    -0.07
    POSITIVE LOGITS
     outage
    0.09
     Inspirational
    0.08
     оплач
    0.08
    Tabela
    0.08
    ueling
    0.08
     condem
    0.08
     Master
    0.08
     Falle
    0.08
     स्क्रीन
    0.07
     ischem
    0.07
    Activations Density 0.020%

    No Known Activations