© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65517
    Prev
    Next
    INDEX
    Explanations

    digits and integers

    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
    (rx
    -0.09
    สนาม
    -0.08
    slick
    -0.08
    (gray
    -0.08
     свет
    -0.08
     rivalry
    -0.08
    asuring
    -0.08
     мировой
    -0.08
     sidewalks
    -0.08
     beaux
    -0.08
    POSITIVE LOGITS
    骰
    0.09
    组合
    0.09
     aliqu
    0.08
     multiplic
    0.08
     dice
    0.08
     odds
    0.08
     distribut
    0.08
     Factors
    0.08
     factors
    0.08
    .product
    0.08
    Activations Density 0.024%

    No Known Activations