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. 43794
    Prev
    Next
    INDEX
    Explanations

    ankle

    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
     corpus
    -0.08
    /entity
    -0.08
    orette
    -0.08
     sofá
    -0.07
     Couch
    -0.07
    -0.07
     شهر
    -0.07
    Nth
    -0.07
     taxable
    -0.07
    (entity
    -0.07
    POSITIVE LOGITS
    _ra
    0.08
    hadow
    0.08
     आंद
    0.08
     étant
    0.08
     mouvements
    0.08
    otni
    0.08
     munk
    0.08
     pipelines
    0.08
     Raptors
    0.08
    wege
    0.08
    Activations Density 0.005%

    No Known Activations