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. 141
    Prev
    Next
    INDEX
    Explanations

    coordinates and diagrams

    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
    i
    -0.08
    endo
    -0.08
     Following
    -0.08
    ಿಯಾದ
    -0.07
    red
    -0.07
     measuring
    -0.07
     End
    -0.07
     At
    -0.07
     following
    -0.07
    ിയായ
    -0.07
    POSITIVE LOGITS
    _cleanup
    0.09
     tertentu
    0.08
     sekitar
    0.08
     ".↵
    0.08
     khusus
    0.08
    _alloc
    0.08
     આધ
    0.08
    _focus
    0.08
    _bonus
    0.08
     معين
    0.08
    Activations Density 0.003%

    No Known Activations