© 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. 112723
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    idagi
    -0.08
    ists
    -0.08
    _gl
    -0.08
    _destroy
    -0.07
    romax
    -0.07
    gl
    -0.07
    atham
    -0.07
    aton
    -0.07
     следующие
    -0.07
    -area
    -0.07
    POSITIVE LOGITS
    。同
    0.09
     電
    0.08
     vrijwill
    0.08
     同
    0.08
     عضو
    0.08
     oneself
    0.08
     болып
    0.08
    鉄
    0.08
     friv
    0.08
     sekal
    0.07
    Activations Density 0.041%

    No Known Activations