Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 27716
    Prev
    Next
    INDEX
    Explanations

    Artificial intelligence and design

    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
     кич
    -0.08
     людьми
    -0.08
     suffer
    -0.08
     дзяржаў
    -0.08
      
    -0.08
     eignen
    -0.07
     жөн
    -0.07
    მე
    -0.07
     clandest
    -0.07
     относятся
    -0.07
    POSITIVE LOGITS
     intelligent
    0.12
     intelligente
    0.12
     assistance
    0.12
     automatiquement
    0.12
     automaticamente
    0.12
     Intelligent
    0.12
     inteligente
    0.11
     intelligently
    0.11
     Assistant
    0.11
     Assistance
    0.11
    Activations Density 0.036%

    No Known Activations