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. 60972
    Prev
    Next
    INDEX
    Explanations

    cuisine

    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
     aprobación
    -0.09
     Galileo
    -0.08
    ilos
    -0.08
     lluvia
    -0.08
     Cody
    -0.08
     घोषणा
    -0.08
    Enumeration
    -0.08
     Isaiah
    -0.08
     Jezus
    -0.08
     बिट
    -0.08
    POSITIVE LOGITS
     cuisine
    0.15
     cuisines
    0.12
     dishes
    0.12
     Cuisine
    0.12
    Cuisine
    0.11
    料理
    0.11
     barbecue
    0.11
     кухня
    0.11
     блюда
    0.10
     comida
    0.10
    Activations Density 0.055%

    No Known Activations