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. 88086
    Prev
    Next
    INDEX
    Explanations

    sentence

    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
     algo
    -0.09
     emprend
    -0.07
     Obama
    -0.07
     gott
    -0.07
     altar
    -0.07
     tuk
    -0.07
     sinó
    -0.07
     durant
    -0.07
     Debbie
    -0.07
    🙏
    -0.07
    POSITIVE LOGITS
    bf
    0.08
     confusing
    0.08
    bold
    0.08
     بـ
    0.08
    是什么意思
    0.07
    ว่า
    0.07
     wording
    0.07
     Additional
    0.07
    后的
    0.07
     bold
    0.07
    Activations Density 0.033%

    No Known Activations