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. 58991
    Prev
    Next
    INDEX
    Explanations

    precise numbers/constants

    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
     أنحاء
    -0.08
    組
    -0.07
     यात्र
    -0.07
    fab
    -0.07
     geschützt
    -0.07
     استط
    -0.07
     sulla
    -0.07
    .Broadcast
    -0.07
     îns
    -0.07
    .nc
    -0.07
    POSITIVE LOGITS
    789
    0.09
    771
    0.09
    340
    0.09
    605
    0.08
    вет
    0.08
    175
    0.08
    .flush
    0.08
     lengthy
    0.08
    omone
    0.08
     balm
    0.08
    Activations Density 0.003%

    No Known Activations