© 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. 71231
    Prev
    Next
    INDEX
    Explanations

    conjugate

    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
     oversight
    -0.08
     trop
    -0.07
    lack
    -0.07
    .sys
    -0.07
     bill
    -0.07
    _interrupt
    -0.07
    icar
    -0.07
    ERVED
    -0.07
     disfr
    -0.07
    Dup
    -0.07
    POSITIVE LOGITS
    詞
    0.08
     DG
    0.08
    ggj
    0.08
    aculate
    0.08
     zj
    0.08
    HO
    0.07
    思思
    0.07
     hh
    0.07
    LOSS
    0.07
     بال
    0.07
    Activations Density 0.003%

    No Known Activations