Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 174
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     Innov
    -0.08
    Execut
    -0.08
    _CP
    -0.08
     فعال
    -0.08
     Creative
    -0.08
     Вол
    -0.08
     creatieve
    -0.08
     تصور
    -0.08
     Казахстан
    -0.08
    Invent
    -0.07
    POSITIVE LOGITS
     steckt
    0.08
    oops
    0.08
    MIC
    0.08
     normale
    0.07
    isierung
    0.07
    electron
    0.07
    tting
    0.07
    에는
    0.07
     rechte
    0.07
     pung
    0.07
    Activations Density 0.023%

    No Known Activations