© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 45557
    Prev
    Next
    INDEX
    Explanations

    probability distributions

    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
    Specify
    -0.08
     sev
    -0.08
     specify
    -0.08
    型号
    -0.07
    Название
    -0.07
    _ng
    -0.07
    _require
    -0.07
    .Abstract
    -0.07
     gekozen
    -0.07
     requis
    -0.07
    POSITIVE LOGITS
    east
    0.08
    ैर
    0.08
     symmetric
    0.08
     Johansson
    0.08
     EAST
    0.08
    र्म
    0.08
     harr
    0.08
     halves
    0.08
     zählen
    0.08
     probabilities
    0.08
    Activations Density 0.011%

    No Known Activations