© 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. 11-RESID-POST-AA
    11. 94797
    Prev
    Next
    INDEX
    Explanations

    ------

    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
     noisy
    -0.08
    кра
    -0.08
     шик
    -0.08
    гу
    -0.08
    аро
    -0.08
    skins
    -0.08
    侵犯
    -0.07
    raw
    -0.07
    арам
    -0.07
     damaged
    -0.07
    POSITIVE LOGITS
     زمن
    0.12
     الزمن
    0.11
    時間
    0.11
     시간
    0.11
     ವೇಳ
    0.11
     시간을
    0.11
    时间
    0.10
     时间
    0.10
     العصر
    0.10
     वेळ
    0.10
    Activations Density 0.013%

    No Known Activations