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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97210
    Prev
    Next
    INDEX
    Explanations

    say "ac"

    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
    ź
    -0.08
     माना
    -0.08
    colleté
    -0.07
     noi
    -0.07
     bayi
    -0.07
    וכים
    -0.07
     पैर
    -0.07
     Société
    -0.07
    .lang
    -0.07
     insulin
    -0.07
    POSITIVE LOGITS
    ac
    0.09
    aczy
    0.08
     ava
    0.08
    avil
    0.08
    owią
    0.08
    acamole
    0.08
    acza
    0.08
     frei
    0.08
     Vim
    0.08
    Datas
    0.07
    Activations Density 0.000%

    No Known Activations