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. 12911
    Prev
    Next
    INDEX
    Explanations

    heat

    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
     guideline
    -0.08
    -types
    -0.08
    Services
    -0.08
     differentiation
    -0.08
     differentiated
    -0.07
    ليات
    -0.07
    Differ
    -0.07
     ansiedad
    -0.07
     serviced
    -0.07
    Expectation
    -0.07
    POSITIVE LOGITS
     extractor
    0.08
     Swap
    0.08
     Opportunity
    0.08
     Extraction
    0.08
     Opportun
    0.08
     extrait
    0.08
     Opportunities
    0.08
     Extract
    0.08
    交换
    0.08
    эконом
    0.08
    Activations Density 0.008%

    No Known Activations