Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19530
    Prev
    Next
    INDEX
    Explanations

    breath fogging

    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
     вер
    -0.08
    -me
    -0.07
    вел
    -0.07
    πεζ
    -0.07
    -
    -0.07
     Sche
    -0.07
     E
    -0.07
     διά
    -0.07
     επισ
    -0.07
     
    -0.07
    POSITIVE LOGITS
     intérieure
    0.08
    uthor
    0.08
     temporarily
    0.08
    (tf
    0.08
     gudaha
    0.08
    ədə
    0.08
    گیرد
    0.08
     되었
    0.08
    deur
    0.08
     ndani
    0.08
    Activations Density 0.001%

    No Known Activations