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. 19055
    Prev
    Next
    INDEX
    Explanations

    Mathematical formulas

    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
    /.↵↵
    -0.10
     आदि
    -0.09
     વગેરે
    -0.09
    ']],↵
    -0.09
    iyanas
    -0.08
    isz
    -0.08
    assaq
    -0.08
    imiwa
    -0.08
    ႏိုင္
    -0.08
    ']],
    -0.08
    POSITIVE LOGITS
    :
    0.09
     those
    0.09
     these
    0.09
     dürfte
    0.08
    stdcall
    0.08
     bovenstaande
    0.08
     STL
    0.08
     Corey
    0.07
     klassische
    0.07
     φα
    0.07
    Activations Density 0.040%

    No Known Activations