© 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. 23-RESID-POST-AA
    11. 5833
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =>
    -0.08
    ERROR
    -0.08
    ROSS
    -0.08
     policeman
    -0.08
    Gym
    -0.08
    vereniging
    -0.08
    开奖结果
    -0.08
    开奖号码
    -0.08
     경찰
    -0.07
     polít
    -0.07
    POSITIVE LOGITS
     Ami
    0.11
    Pct
    0.10
     ykn
    0.09
     nag
    0.09
    Slf
    0.09
     Css
    0.09
     Ast
    0.09
     ato
    0.09
     Tar
    0.09
     tsa
    0.09
    Activations Density 0.002%

    No Known Activations