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. 19381
    Prev
    Next
    INDEX
    Explanations

    say "4"

    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
     a
    -0.08
    :↵↵
    -0.08
     an
    -0.08
    ,
    -0.08
    genre
    -0.07
     or
    -0.07
     genres
    -0.07
     popular
    -0.07
    fullname
    -0.07
     besonderes
    -0.07
    POSITIVE LOGITS
     самостоятель
    0.10
    是什么意思
    0.09
    διά
    0.09
     అంటే
    0.09
    că
    0.08
    -earned
    0.08
    тесь
    0.08
    -dist
    0.08
     olun
    0.08
    -solving
    0.08
    Activations Density 0.001%

    No Known Activations