© 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. 97228
    Prev
    Next
    INDEX
    Explanations

    情

    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
    issait
    -0.08
    μία
    -0.08
    ાણ
    -0.08
     éch
    -0.08
    aimana
    -0.08
    ाण
    -0.08
    υμα
    -0.08
     struggling
    -0.07
    수를
    -0.07
    azụ
    -0.07
    POSITIVE LOGITS
    节
    0.09
    有
    0.09
    急
    0.08
     الآ
    0.08
     voluntad
    0.08
    愿
    0.08
    ovn
    0.08
    情
    0.07
    加
    0.07
    fld
    0.07
    Activations Density 0.001%

    No Known Activations