© 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. 23-RESID-POST-AA
    11. 49308
    Prev
    Next
    INDEX
    Explanations

    say "í" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مقدار
    -0.08
    овом
    -0.08
    .debug
    -0.08
    ોમ
    -0.08
     sprem
    -0.07
    .Edit
    -0.07
    отой
    -0.07
    isele
    -0.07
    ово
    -0.07
    Navigate
    -0.07
    POSITIVE LOGITS
     Attr
    0.09
    Topology
    0.08
    _UID
    0.08
    (attr
    0.08
    ージ
    0.08
    itas
    0.08
     whitelist
    0.08
    _TOP
    0.07
     ciudadanía
    0.07
    attr
    0.07
    Activations Density 0.000%

    No Known Activations