© 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. 18457
    Prev
    Next
    INDEX
    Explanations

    say "vanilla"

    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
     squares
    -0.09
    Qs
    -0.08
    SWEP
    -0.08
    meti
    -0.08
    Squares
    -0.08
    martes
    -0.08
     pressures
    -0.08
     reconnect
    -0.08
     salads
    -0.08
     redes
    -0.08
    POSITIVE LOGITS
     vanilla
    0.23
     Vanilla
    0.19
     esencia
    0.17
     extract
    0.16
     ван
    0.16
    Van
    0.16
    香
    0.15
    _extract
    0.15
     Extract
    0.15
     bourbon
    0.15
    Activations Density 0.007%

    No Known Activations