© 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. 11-RESID-POST-AA
    11. 110897
    Prev
    Next
    INDEX
    Explanations

    sake

    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
    cel
    -0.08
    ocr
    -0.07
    389
    -0.07
    aur
    -0.07
    unca
    -0.07
    _has
    -0.07
     leash
    -0.07
    opp
    -0.07
    erca
    -0.07
     visited
    -0.07
    POSITIVE LOGITS
     पानी
    0.08
     dwar
    0.08
     воду
    0.08
     вод
    0.08
    geno
    0.08
     పుర
    0.08
     القيمة
    0.08
     matlab
    0.07
    .Marshal
    0.07
    .Maximum
    0.07
    Activations Density 0.002%

    No Known Activations