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. 53136
    Prev
    Next
    INDEX
    Explanations

    2

    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
    지만
    -0.08
     thermal
    -0.08
     presentar
    -0.08
    Vendor
    -0.08
     rés
    -0.08
    thermal
    -0.08
    introduced
    -0.08
     XR
    -0.08
     floats
    -0.07
    .inter
    -0.07
    POSITIVE LOGITS
     undefined
    0.08
     alb
    0.08
    狼人
    0.08
    (A
    0.07
     derivative
    0.07
    ^
    0.07
     patri
    0.07
     astrolog
    0.07
    unciation
    0.07
     homo
    0.07
    Activations Density 0.016%

    No Known Activations