© 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. 11-RESID-POST-AA
    11. 70678
    Prev
    Next
    INDEX
    Explanations

    acrostic poems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Thierry
    -0.07
     reconc
    -0.07
     ne
    -0.07
     ephemeral
    -0.07
     comes
    -0.07
     secondary
    -0.07
     więcej
    -0.07
     has
    -0.07
    .secondary
    -0.07
    .↵↵
    -0.06
    POSITIVE LOGITS
     acronym
    0.14
     abbreviation
    0.11
    (letter
    0.09
     গু
    0.09
     letters
    0.09
    անտ
    0.09
     беҙҙең
    0.09
    yh
    0.09
    izma
    0.09
    стың
    0.09
    Activations Density 0.096%

    No Known Activations