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. 111990
    Prev
    Next
    INDEX
    Explanations

    php

    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
     reachable
    -0.08
     mutex
    -0.08
    Spend
    -0.07
    reich
    -0.07
     memorandum
    -0.07
     انگی
    -0.07
    aria
    -0.07
     ब्रिट
    -0.07
     associ
    -0.07
     kiiresti
    -0.07
    POSITIVE LOGITS
    templates
    0.09
    ɛ
    0.08
     templates
    0.08
     qualities
    0.08
    qualities
    0.08
    /templates
    0.08
    template
    0.08
    ο
    0.08
     шаб
    0.07
    shof
    0.07
    Activations Density 0.004%

    No Known Activations