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. 9026
    Prev
    Next
    INDEX
    Explanations

    definitions, conventions

    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
    >M
    -0.08
     Rochester
    -0.08
    -border
    -0.07
    -opening
    -0.07
     هد
    -0.07
    -the
    -0.07
     practically
    -0.07
    eer
    -0.07
    -themed
    -0.07
     فتح
    -0.07
    POSITIVE LOGITS
     convenience
    0.08
     gewählt
    0.08
     convention
    0.08
     customary
    0.08
     conventions
    0.08
     방식
    0.08
     traditionally
    0.08
     sehingga
    0.08
    方便
    0.08
    便利
    0.08
    Activations Density 0.053%

    No Known Activations