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. 49316
    Prev
    Next
    INDEX
    Explanations

    divisibility tests

    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
    사는
    -0.09
    gender
    -0.09
    사의
    -0.08
    itters
    -0.08
    Gender
    -0.08
    Determ
    -0.08
    ellipse
    -0.08
    사를
    -0.07
    가는
    -0.07
     sexist
    -0.07
    POSITIVE LOGITS
     promoción
    0.09
     promoção
    0.08
     टाइम
    0.08
     decoder
    0.08
     Folding
    0.07
    ugin
    0.07
     Alternate
    0.07
     subtraction
    0.07
     Infinity
    0.07
     televisión
    0.07
    Activations Density 0.013%

    No Known Activations