© 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. 18489
    Prev
    Next
    INDEX
    Explanations

    Delimiters

    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
     Jaz
    -0.08
     requis
    -0.07
     a
    -0.07
     dari
    -0.07
    .Override
    -0.07
     ника
    -0.07
     jist
    -0.07
    .Spec
    -0.07
     spes
    -0.07
     populer
    -0.07
    POSITIVE LOGITS
     ',',
    0.14
    delimiter
    0.14
     ')[
    0.13
     delimiter
    0.12
     delim
    0.12
    (','
    0.12
    Delimiter
    0.12
    (',',
    0.11
     delimit
    0.11
    ')[
    0.11
    Activations Density 0.004%

    No Known Activations