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. 58898
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
    _feed
    -0.09
     ಸಲ
    -0.08
     советы
    -0.08
     кав
    -0.08
     Feed
    -0.07
    cke
    -0.07
     feed
    -0.07
     Drives
    -0.07
    397
    -0.07
     zusammeng
    -0.07
    POSITIVE LOGITS
     vague
    0.13
     vaguely
    0.10
     ambiguous
    0.09
    Unknown
    0.09
     unknown
    0.08
     загад
    0.08
    未知
    0.08
    ;n
    0.08
     unresolved
    0.08
     qualitative
    0.08
    Activations Density 0.070%

    No Known Activations