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. 19271
    Prev
    Next
    INDEX
    Explanations

    Assistance request

    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
     allegedly
    -0.11
     aparentemente
    -0.10
     reportedly
    -0.10
     apparently
    -0.10
     seemingly
    -0.09
     Apparently
    -0.09
    ીઆ
    -0.09
     ostens
    -0.09
    ↵      ↵
    -0.09
    Classpath
    -0.09
    POSITIVE LOGITS
     want
    0.11
     the
    0.10
     يكون
    0.10
     מדובר
    0.10
     easiest
    0.10
    来说
    0.09
     تكون
    0.09
     потому
    0.09
    情况下
    0.09
     refers
    0.08
    Activations Density 0.047%

    No Known Activations