© 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 EvalsExportsAPI 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. 42988
    Prev
    Next
    INDEX
    Explanations

    base

    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
    madan
    -0.08
     Deel
    -0.08
     gaf
    -0.08
    .cleaned
    -0.08
     unter
    -0.08
     Intro
    -0.08
    .cert
    -0.08
    .Completed
    -0.08
     بده
    -0.07
     Des
    -0.07
    POSITIVE LOGITS
     radix
    0.10
    -base
    0.09
     numeral
    0.08
     perust
    0.08
    achi
    0.08
     આધાર
    0.08
     branching
    0.08
    _BASE
    0.08
     осн
    0.07
     негіз
    0.07
    Activations Density 0.034%

    No Known Activations