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. 54088
    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
    伙伴
    -0.09
     premios
    -0.08
     measurable
    -0.07
     frågor
    -0.07
    leased
    -0.07
     sibling
    -0.07
    Prem
    -0.07
     Apps
    -0.07
     רבה
    -0.07
    iyot
    -0.07
    POSITIVE LOGITS
     বিস্তারিত
    0.08
     railing
    0.08
     ಕನ
    0.08
    orang
    0.07
    /interface
    0.07
    رج
    0.07
     ধারণ
    0.07
     imagining
    0.07
     icy
    0.07
     Szene
    0.07
    Activations Density 0.003%

    No Known Activations