© 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. 114282
    Prev
    Next
    INDEX
    Explanations

    large quantities or durations

    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
     lex
    -0.08
    ican
    -0.08
     Wol
    -0.08
     tutorial
    -0.08
     tark
    -0.08
    issor
    -0.07
     expliqué
    -0.07
     laure
    -0.07
     blah
    -0.07
    .lex
    -0.07
    POSITIVE LOGITS
     Enough
    0.09
     respectable
    0.09
    Enough
    0.08
    stantial
    0.08
     genügend
    0.08
     상당
    0.08
     যথ
    0.08
    不足
    0.08
     충분
    0.08
    Typical
    0.08
    Activations Density 0.089%

    No Known Activations