Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 102762
    Prev
    Next
    INDEX
    Explanations

    Vue

    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
    יים
    -0.09
     conditioning
    -0.08
     כל
    -0.07
    дя
    -0.07
     зм
    -0.07
    ומי
    -0.07
     שמ
    -0.07
     Reid
    -0.07
     initializer
    -0.07
    Modifiers
    -0.07
    POSITIVE LOGITS
    /vue
    0.09
    (Vue
    0.09
     mongoose
    0.08
     Ther
    0.08
     Barang
    0.08
     lighten
    0.08
     Firma
    0.07
     相
    0.07
     Band
    0.07
     tienda
    0.07
    Activations Density 0.003%

    No Known Activations