© 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. 97438
    Prev
    Next
    INDEX
    Explanations

    say "choose"

    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
    iliation
    -0.08
    liği
    -0.08
     וה
    -0.08
    லி
    -0.08
    vasion
    -0.08
    atsira
    -0.07
     questa
    -0.07
     olması
    -0.07
    监听页面
    -0.07
     الوف
    -0.07
    POSITIVE LOGITS
     choose
    0.42
    choose
    0.36
    Choose
    0.33
     Choose
    0.33
    _choose
    0.31
    .choose
    0.28
     choisissez
    0.26
     choisir
    0.24
     escolher
    0.24
    C
    0.24
    Activations Density 0.057%

    No Known Activations