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. 78552
    Prev
    Next
    INDEX
    Explanations

    索

    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
     reboot
    -0.08
    .Throws
    -0.07
     rows
    -0.07
     Frankreich
    -0.07
    .Localization
    -0.07
    Rows
    -0.07
    .rows
    -0.07
    Recipes
    -0.07
    idors
    -0.07
    _org
    -0.07
    POSITIVE LOGITS
     instrumento
    0.08
     instrumentation
    0.08
     Instrument
    0.08
    -enabled
    0.08
     wish
    0.08
     Hopefully
    0.07
     түрде
    0.07
     adc
    0.07
     жақсы
    0.07
     domicili
    0.07
    Activations Density 0.001%

    No Known Activations