© 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. 19109
    Prev
    Next
    INDEX
    Explanations

    say "number 1"

    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
     relatively
    -0.14
     modest
    -0.13
     moderate
    -0.12
     moderately
    -0.12
     relativamente
    -0.12
     relatief
    -0.11
     comparatively
    -0.11
     небольш
    -0.11
     reasonably
    -0.10
     maliit
    -0.10
    POSITIVE LOGITS
     ridiculously
    0.11
     one
    0.11
     One
    0.11
    .one
    0.10
    .One
    0.10
    one
    0.10
    _one
    0.10
     Twitter
    0.10
     Very
    0.10
     ultra
    0.10
    Activations Density 0.019%

    No Known Activations