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. 15-RESID-POST-AA
    6. 19355
    Prev
    Next
    INDEX
    Explanations

    Entirety/positivity

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interoperability
    -0.09
     interoper
    -0.08
     Brother
    -0.07
     interchangeable
    -0.07
    具体
    -0.07
     FAIR
    -0.07
     Scratch
    -0.07
    参与
    -0.07
    到
    -0.07
     facilitate
    -0.07
    POSITIVE LOGITS
     monoton
    0.11
     monot
    0.11
     toàn
    0.11
     positivity
    0.11
    Entire
    0.11
     全天
    0.10
     全
    0.10
     throughout
    0.10
     entirely
    0.10
    Throughout
    0.10
    Activations Density 0.046%

    No Known Activations