© 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. 18578
    Prev
    Next
    INDEX
    Explanations

    numeric data types

    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
    letas
    -0.08
    -0.08
    казать
    -0.08
    leté
    -0.07
    ácil
    -0.07
    总代
    -0.07
    leta
    -0.07
     glfw
    -0.07
    absch
    -0.07
    LETE
    -0.07
    POSITIVE LOGITS
     numeric
    0.14
    numeric
    0.14
    _numeric
    0.12
     varchar
    0.12
     Numeric
    0.12
    .numeric
    0.12
    Numeric
    0.11
    704
    0.11
     erkannt
    0.11
     stored
    0.10
    Activations Density 0.007%
    No Known Activations