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. 55950
    Prev
    Next
    INDEX
    Explanations

    code and programming snippets

    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
     এখানে
    -0.08
            	
    -0.08
     większo
    -0.08
    Spirit
    -0.08
    原则
    -0.08
     basically
    -0.08
     ಇಲ್ಲಿ
    -0.08
     снижение
    -0.07
     siellä
    -0.07
     essentially
    -0.07
    POSITIVE LOGITS
    Multiple
    0.09
     Custom
    0.09
     polish
    0.08
     Multiple
    0.08
    もっと
    0.08
     debugging
    0.08
     personalizados
    0.08
     Improvements
    0.08
    _custom
    0.08
     Scal
    0.08
    Activations Density 0.043%

    No Known Activations