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. 59549
    Prev
    Next
    INDEX
    Explanations

    Schwa

    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
    וחה
    -0.08
     calculation
    -0.08
    onomous
    -0.07
     monopol
    -0.07
     denominada
    -0.07
    ocratic
    -0.07
     captura
    -0.07
     Permanente
    -0.07
     Comm
    -0.07
    ancer
    -0.07
    POSITIVE LOGITS
     kyr
    0.08
     fragrance
    0.08
    .↵↵//
    0.07
     další
    0.07
     ROW
    0.07
    \Routing
    0.07
     أيضاً
    0.07
    /...
    0.07
     ='
    0.07
    ياتي
    0.07
    Activations Density 0.012%

    No Known Activations