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. 56
    Prev
    Next
    INDEX
    Explanations

    we

    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
    REFERENCE
    -0.10
     Dienst
    -0.09
    WAIT
    -0.09
     alapján
    -0.09
     ואז
    -0.09
     관광
    -0.09
    ึ่ง
    -0.09
     우리는
    -0.08
    urrican
    -0.08
    ährt
    -0.08
    POSITIVE LOGITS
    不要
    0.10
     avoid
    0.09
     be
    0.09
     refrain
    0.09
     silo
    0.08
    不能
    0.08
    不用
    0.08
     use
    0.08
    避免
    0.08
     to
    0.08
    Activations Density 0.003%

    No Known Activations