Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98649
    Prev
    Next
    INDEX
    Explanations

    networking layers

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     smooth
    -0.07
     group
    -0.07
    延期
    -0.07
     histoires
    -0.07
     delin
    -0.07
    里的
    -0.07
    gatsby
    -0.07
    历史
    -0.07
     stools
    -0.07
     embryos
    -0.07
    POSITIVE LOGITS
    ၇
    0.10
    ۷
    0.10
     näk
    0.10
    	os
    0.09
    raising
    0.09
    ૭
    0.09
    	lock
    0.09
    ٧
    0.09
     الثالثة
    0.09
    <th
    0.09
    Activations Density 0.002%

    No Known Activations