© 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. 78442
    Prev
    Next
    INDEX
    Explanations

    user

    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
    Inherited
    -0.08
     inherited
    -0.08
     linguistic
    -0.08
    Liquidity
    -0.07
     Lancashire
    -0.07
     convention
    -0.07
     Lingu
    -0.07
     recession
    -0.07
     Lansing
    -0.07
    nown
    -0.07
    POSITIVE LOGITS
    违反
    0.09
     hateful
    0.09
     violates
    0.09
    は禁止
    0.09
    是否合法
    0.09
     illicit
    0.09
     flagr
    0.08
     intox
    0.08
    作弊
    0.08
    合法
    0.08
    Activations Density 0.023%

    No Known Activations