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. 12860
    Prev
    Next
    INDEX
    Explanations

    question answering

    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
    老板
    -0.09
     yaklaş
    -0.09
    索
    -0.08
     empresários
    -0.08
     tarkoit
    -0.08
    _players
    -0.08
    vais
    -0.08
    yam
    -0.08
     undertaken
    -0.07
     approached
    -0.07
    POSITIVE LOGITS
     features
    0.11
     Features
    0.10
     особенности
    0.10
    features
    0.09
     phenomena
    0.09
     특징
    0.09
    ميزات
    0.09
     отличие
    0.09
     Exclusive
    0.08
     fonctionnalités
    0.08
    Activations Density 0.072%

    No Known Activations