© 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. 3-RESID-POST-AA
    11. 2746
    Prev
    Next
    INDEX
    Explanations

    ug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spaper
    -0.08
    ールド
    -0.08
    (Group
    -0.08
    Gab
    -0.08
     Occup
    -0.07
     مکان
    -0.07
     ジ
    -0.07
     স্থান
    -0.07
    仕
    -0.07
     Gregory
    -0.07
    POSITIVE LOGITS
    ices
    0.08
    veis
    0.08
     raffin
    0.07
     Smartphones
    0.07
    .SERVER
    0.07
    wissen
    0.07
     cope
    0.07
    _BUF
    0.07
    姐妹
    0.07
     Funcion
    0.07
    Activations Density 0.003%

    No Known Activations