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. 53142
    Prev
    Next
    INDEX
    Explanations

    pyramid

    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
     Detox
    -0.08
     storm
    -0.08
    storm
    -0.08
    Storm
    -0.07
    /Base
    -0.07
    .work
    -0.07
     gemeinsam
    -0.07
     за
    -0.07
     mencion
    -0.07
     Donovan
    -0.07
    POSITIVE LOGITS
     pelvis
    0.10
     adhered
    0.08
    Sides
    0.07
     sides
    0.07
     adjacency
    0.07
    (double
    0.07
    RNA
    0.07
    Sens
    0.07
     aft
    0.07
    0.07
    Activations Density 0.003%

    No Known Activations