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. 11-RESID-POST-AA
    6. 44024
    Prev
    Next
    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     север
    -0.08
    -inspired
    -0.08
     Tacoma
    -0.08
    Blog
    -0.08
    Dock
    -0.08
    Mot
    -0.08
     secluded
    -0.08
     получила
    -0.08
     miles
    -0.08
     получил
    -0.07
    POSITIVE LOGITS
    考试
    0.11
     questionnaire
    0.10
     Vietnamese
    0.10
     Indonesian
    0.09
    干部
    0.09
     questionnaires
    0.09
    _dropdown
    0.09
     quiz
    0.09
     QUESTION
    0.09
     classifiers
    0.09
    Activations Density 0.118%

    No Known Activations