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. 23-RESID-POST-AA
    6. 98074
    Prev
    Next
    INDEX
    Explanations

    но

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    j
    -0.09
     arrep
    -0.08
    לית
    -0.08
    ανα
    -0.08
     ನಿರ
    -0.08
     epithelial
    -0.08
    น
    -0.08
     ತರ
    -0.08
     dermed
    -0.08
     optreden
    -0.08
    POSITIVE LOGITS
    šenje
    0.12
    сятся
    0.12
    isseurs
    0.11
    сим
    0.10
    туу
    0.10
    šenja
    0.10
    isseur
    0.10
    сят
    0.09
    ските
    0.09
    ску
    0.09
    Activations Density 0.003%

    No Known Activations