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. 60680
    Prev
    Next
    INDEX
    Explanations

    habits

    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
     sumi
    -0.08
     النس
    -0.08
     fotografía
    -0.08
     Summer
    -0.08
     fotografías
    -0.07
     photographs
    -0.07
    Side
    -0.07
     COS
    -0.07
     Side
    -0.07
     Heavy
    -0.07
    POSITIVE LOGITS
     findes
    0.08
    决定
    0.07
    Predict
    0.07
     embracing
    0.07
     sindic
    0.07
     двер
    0.07
     Businesses
    0.07
     рул
    0.07
    Loader
    0.07
    wala
    0.07
    Activations Density 0.002%

    No Known Activations