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. 12089
    Prev
    Next
    INDEX
    Explanations

    depth

    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
    themes
    -0.08
     ethnic
    -0.08
     annotations
    -0.07
     trends
    -0.07
     oral
    -0.07
     sentiments
    -0.07
     themes
    -0.07
     mọi
    -0.07
    bio
    -0.07
     cadres
    -0.07
    POSITIVE LOGITS
    �
    0.10
     게시
    0.09
     Require
    0.09
     감독
    0.08
     체크
    0.08
     REQUIRE
    0.08
    steen
    0.08
    خة
    0.08
     Suomen
    0.08
    ادة
    0.08
    Activations Density 0.001%

    No Known Activations