© 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. 23-RESID-POST-AA
    11. 51085
    Prev
    Next
    INDEX
    Explanations

    816

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eps
    -0.08
     Sort
    -0.07
     sort
    -0.07
    eps
    -0.07
     રાહ
    -0.07
    阻
    -0.07
    .Refresh
    -0.07
     loaders
    -0.07
    -block
    -0.07
    _eps
    -0.07
    POSITIVE LOGITS
    ovane
    0.09
     tap
    0.08
     cómod
    0.08
     прили
    0.08
    partum
    0.08
    曰
    0.08
    akaran
    0.08
     boils
    0.08
     Laurel
    0.08
    すす
    0.08
    Activations Density 0.000%

    No Known Activations