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. 60854
    Prev
    Next
    INDEX
    Explanations

    photographic

    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
    lir
    -0.08
    -tax
    -0.07
    redentials
    -0.07
     rebel
    -0.07
     routing
    -0.07
     Geist
    -0.07
    -routing
    -0.07
    ustan
    -0.07
     reconciliation
    -0.07
    сли
    -0.07
    POSITIVE LOGITS
    Grab
    0.09
    Pickup
    0.08
     grab
    0.08
    grab
    0.08
     Grab
    0.08
     모습
    0.08
     камера
    0.08
     grabbed
    0.08
    Canonical
    0.08
     कैम
    0.07
    Activations Density 0.010%

    No Known Activations