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. 56287
    Prev
    Next
    INDEX
    Explanations

    the

    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
     inviting
    -0.08
    BAB
    -0.07
    ಿಟ್ಟ
    -0.07
    ونو
    -0.07
     открыт
    -0.07
    াদের
    -0.07
     lately
    -0.07
    ्रा
    -0.07
     nowadays
    -0.07
    勤
    -0.07
    POSITIVE LOGITS
     stripped
    0.09
    _strip
    0.09
     eliminar
    0.09
     unterwegs
    0.08
    _after
    0.08
    _AFTER
    0.08
     perjalanan
    0.08
     hop
    0.08
    .Immutable
    0.08
    .Tuple
    0.08
    Activations Density 0.013%

    No Known Activations