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. 30735
    Prev
    Next
    INDEX
    Explanations

    Books and literature

    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
     congest
    -0.08
    ayaran
    -0.08
    ,:,
    -0.08
     freel
    -0.08
     floating
    -0.07
    floating
    -0.07
     للخ
    -0.07
     pembayaran
    -0.07
     transmitting
    -0.07
     oily
    -0.07
    POSITIVE LOGITS
     classroom
    0.10
     Classroom
    0.10
    Wrapper
    0.10
     Wrapper
    0.09
     wrapper
    0.09
     wrappers
    0.09
     мектеп
    0.09
     textbooks
    0.09
    包装
    0.09
     చద
    0.09
    Activations Density 0.052%

    No Known Activations