© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69279
    Prev
    Next
    INDEX
    Explanations

    So

    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
    ).↵↵↵
    -0.07
     その他
    -0.07
    /gl
    -0.07
     lenght
    -0.07
    ащ
    -0.07
     finder
    -0.07
    WARD
    -0.07
     Transform
    -0.07
    ood
    -0.07
    animations
    -0.07
    POSITIVE LOGITS
    今晚
    0.09
     adjunct
    0.09
    终于
    0.08
    今日
    0.08
     perfected
    0.08
     Tonight
    0.08
    Today's
    0.07
     Egypt
    0.07
     tonight
    0.07
    오늘
    0.07
    Activations Density 0.043%

    No Known Activations