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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 44017
    Prev
    Next
    INDEX
    Explanations

    upgrade

    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
     bul
    -0.08
    伏
    -0.08
     Hat
    -0.08
    лык
    -0.07
    ימת
    -0.07
    Vin
    -0.07
     направ
    -0.07
     vin
    -0.07
     besl
    -0.07
    увати
    -0.07
    POSITIVE LOGITS
    后的
    0.08
     версии
    0.08
    版
    0.08
    .VERSION
    0.08
    .speed
    0.08
     besteh
    0.08
    -than
    0.08
    _version
    0.08
    .version
    0.07
    换
    0.07
    Activations Density 0.015%

    No Known Activations