© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64811
    Prev
    Next
    INDEX
    Explanations

    shirt descriptions

    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
     prese
    -0.08
     Admissions
    -0.08
     civilizations
    -0.08
     Terror
    -0.08
    _GRAPH
    -0.08
     вын
    -0.07
    影视
    -0.07
     outages
    -0.07
     bash
    -0.07
     Borrow
    -0.07
    POSITIVE LOGITS
     breathable
    0.11
     katoen
    0.10
     readability
    0.09
    材
    0.09
     denim
    0.09
    orphic
    0.09
     Baumw
    0.09
    (description
    0.09
     ткани
    0.09
    素材
    0.08
    Activations Density 0.035%

    No Known Activations