© 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. 749
    Prev
    Next
    INDEX
    Explanations

    deny

    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
    技巧
    -0.10
    raints
    -0.08
    _solver
    -0.08
    jie
    -0.08
     Bez
    -0.08
    _constraint
    -0.08
     Dirty
    -0.08
    袋
    -0.08
     oploss
    -0.08
    pon
    -0.08
    POSITIVE LOGITS
     denied
    0.10
     outright
    0.09
     unauthorized
    0.09
     deny
    0.09
    deny
    0.09
     verzoek
    0.09
     rejects
    0.09
     denies
    0.09
     localhost
    0.09
     denying
    0.08
    Activations Density 0.006%

    No Known Activations