© 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. 129502
    Prev
    Next
    INDEX
    Explanations

    x

    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
    利益
    -0.09
     fishermen
    -0.09
     firm
    -0.08
    付款
    -0.08
    组织
    -0.08
    кой
    -0.07
    締
    -0.07
     ultrasound
    -0.07
    Punch
    -0.07
     fibr
    -0.07
    POSITIVE LOGITS
     azon
    0.09
     Celsius
    0.09
    ials
    0.08
    mey
    0.08
     상승
    0.08
     transcend
    0.08
     Gerr
    0.08
     Če
    0.08
     sech
    0.08
     NOR
    0.08
    Activations Density 0.018%

    No Known Activations