© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18725
    Prev
    Next
    INDEX
    Explanations

    uncommon symbols in text

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __.'/
    -0.08
    ̈
    -0.08
    ::__
    -0.08
    __:
    -0.08
    ::.
    -0.08
    WWW
    -0.07
    َا
    -0.07
    !),
    -0.07
    !important
    -0.07
    ☆
    -0.07
    POSITIVE LOGITS
    的问题
    0.11
     вероятность
    0.11
     הראשון
    0.09
    	the
    0.09
     capacidad
    0.08
     האפשר
    0.08
    问题
    0.08
    authorize
    0.08
     Brief
    0.08
     உயர
    0.08
    Activations Density 0.000%

    No Known Activations