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

    Neuronpedia

    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. 25969
    Prev
    Next
    INDEX
    Explanations

    In

    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
     зді
    -0.08
     immerse
    -0.08
     []↵↵
    -0.08
    /es
    -0.08
    او
    -0.08
     argv
    -0.08
     मुद्द
    -0.08
     повышение
    -0.07
     власти
    -0.07
     власть
    -0.07
    POSITIVE LOGITS
     planar
    0.10
    上述
    0.09
    情况下
    0.09
    variants
    0.08
    appropriate
    0.08
    ய
    0.07
     reciprocal
    0.07
     Kik
    0.07
    0.07
     Rutherford
    0.07
    Activations Density 0.029%
    No Known Activations