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. 23
    Prev
    Next
    INDEX
    Explanations

    of

    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
    或者
    -0.09
     või
    -0.08
     oubyen
    -0.08
    等等
    -0.08
     ecstatic
    -0.08
     commercials
    -0.07
     немесе
    -0.07
     famous
    -0.07
     célè
    -0.07
     motives
    -0.07
    POSITIVE LOGITS
    截至
    0.15
     सितंबर
    0.15
     September
    0.13
     সেপ্টেম্বর
    0.13
    ,截至
    0.13
    ২০২
    0.13
    202
    0.13
     ©
    0.12
     itib
    0.12
     नवंबर
    0.11
    Activations Density 0.007%

    No Known Activations