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. 12137
    Prev
    Next
    INDEX
    Explanations

    Dangers and hazards

    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
    _views
    -0.08
     dnes
    -0.08
    merkt
    -0.08
     views
    -0.08
    不错
    -0.08
     النظر
    -0.08
    Elastic
    -0.08
    以来
    -0.07
    	post
    -0.07
    Consent
    -0.07
    POSITIVE LOGITS
     hazards
    0.15
     dangers
    0.14
     obstacles
    0.13
     hostile
    0.12
     hazardous
    0.12
     hiểm
    0.11
    险
    0.11
     perigos
    0.11
     difficulties
    0.11
    危险
    0.11
    Activations Density 0.034%

    No Known Activations