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. 15-RESID-POST-AA
    6. 19089
    Prev
    Next
    INDEX
    Explanations

    times

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     არაფერი
    -0.08
     ontbreken
    -0.08
     არაფ
    -0.08
     درمان
    -0.08
     ούτε
    -0.08
    δήποτε
    -0.07
     denuncia
    -0.07
     Insolvenz
    -0.07
     denial
    -0.07
     არც
    -0.07
    POSITIVE LOGITS
     Powered
    0.09
     ajust
    0.08
     March
    0.08
     fundamental
    0.08
    Powered
    0.08
    March
    0.07
    玻
    0.07
    <$
    0.07
     fondamentale
    0.07
     fundamentales
    0.07
    Activations Density 0.003%

    No Known Activations