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. 158
    Prev
    Next
    INDEX
    Explanations

    St. Francis

    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
     достой
    -0.08
    .~
    -0.08
     verano
    -0.08
     المحلي
    -0.07
    untime
    -0.07
     содержащ
    -0.07
    .circle
    -0.07
     entreten
    -0.07
     collectif
    -0.07
     consistent
    -0.07
    POSITIVE LOGITS
    ымі
    0.08
     börja
    0.08
     fua
    0.08
     näyttää
    0.08
     এসে
    0.08
     ধর
    0.07
    elkast
    0.07
     beina
    0.07
    ეობ
    0.07
     Vast
    0.07
    Activations Density 0.000%

    No Known Activations