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. 19166
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
     dali
    -0.09
     strapped
    -0.09
     plotted
    -0.08
     пришлось
    -0.08
     дали
    -0.08
    ":["
    -0.08
     ecs
    -0.08
     punto
    -0.08
    -case
    -0.08
     waardoor
    -0.08
    POSITIVE LOGITS
     احترام
    0.11
     striving
    0.10
     fostering
    0.10
     尊
    0.10
     بسیاری
    0.10
     важно
    0.10
     strive
    0.09
     promoting
    0.09
     professions
    0.09
     sincerely
    0.09
    Activations Density 0.020%

    No Known Activations