Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77858
    Prev
    Next
    INDEX
    Explanations

    coat

    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
    HEX
    -0.08
    ším
    -0.08
    chip
    -0.08
    emann
    -0.08
    restr
    -0.07
    580
    -0.07
    וא
    -0.07
    inox
    -0.07
    agonal
    -0.07
    wadi
    -0.07
    POSITIVE LOGITS
    下载安装
    0.10
     sosai
    0.09
     brightly
    0.09
     banget
    0.09
     baixar
    0.09
     순간
    0.08
     الجميع
    0.08
     Особенно
    0.08
    程度
    0.08
     kakhulu
    0.08
    Activations Density 0.004%

    No Known Activations