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. 44129
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    など
    -0.08
    (start
    -0.08
    sleep
    -0.08
     Marka
    -0.08
    upt
    -0.08
     Els
    -0.07
     Principles
    -0.07
    (url
    -0.07
     conse
    -0.07
     markii
    -0.07
    POSITIVE LOGITS
    Coefficient
    0.10
     coefficient
    0.09
     coeff
    0.09
     coefficients
    0.09
     উচিত
    0.08
    Coeff
    0.08
    izante
    0.08
    coeff
    0.08
     LIB
    0.08
    ,应
    0.07
    Activations Density 0.047%

    No Known Activations