© 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. 29501
    Prev
    Next
    INDEX
    Explanations

    List manipulation in programming

    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
     бесплатно
    -0.09
     Noah
    -0.08
    额度
    -0.08
     Zestimate
    -0.08
    롯
    -0.08
     봉
    -0.08
    žnost
    -0.08
    ంట్
    -0.08
     제공
    -0.08
    .Other
    -0.08
    POSITIVE LOGITS
    _REMOVE
    0.08
     Removes
    0.08
     remov
    0.08
     Concurrent
    0.08
    .Remove
    0.08
     删除
    0.08
    ュー
    0.08
    Удал
    0.08
     removed
    0.08
    删除
    0.08
    Activations Density 0.002%

    No Known Activations