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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88264
    Prev
    Next
    INDEX
    Explanations

    ather

    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
    .up
    -0.08
     Syl
    -0.08
     Pere
    -0.08
     Mith
    -0.08
     Hulk
    -0.08
     peso
    -0.07
    _pin
    -0.07
    -0.07
    earched
    -0.07
    imy
    -0.07
    POSITIVE LOGITS
    DBNull
    0.08
     envision
    0.08
    اربة
    0.08
     اليوم
    0.08
    赏
    0.08
    ระบบ
    0.08
    unterricht
    0.08
     Veranstaltung
    0.08
    ದುಕೊಂಡ
    0.08
     الأمر
    0.08
    Activations Density 0.003%

    No Known Activations