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. 76587
    Prev
    Next
    INDEX
    Explanations

    lists and tables

    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
    _pre
    -0.08
    ース
    -0.08
    ика
    -0.07
    _ne
    -0.07
     연
    -0.07
     πριν
    -0.07
     رفتار
    -0.07
    ->{'
    -0.06
     précéd
    -0.06
    ಿಸಿದ್ದಾರೆ
    -0.06
    POSITIVE LOGITS
    bibli
    0.08
     alty
    0.08
    累计
    0.08
     barric
    0.08
     rumores
    0.08
     acontecimentos
    0.08
     calendario
    0.08
    Firma
    0.08
     erste
    0.08
    phasis
    0.08
    Activations Density 0.048%

    No Known Activations