© 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. 78016
    Prev
    Next
    INDEX
    Explanations

    Greek

    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
    /path
    -0.08
     matéri
    -0.08
    lists
    -0.08
     fleeting
    -0.07
    ני
    -0.07
     atrop
    -0.07
     routes
    -0.07
     reign
    -0.07
     sublim
    -0.07
    _RDONLY
    -0.07
    POSITIVE LOGITS
     yoghurt
    0.11
     yogurt
    0.10
     cij
    0.08
     Vat
    0.08
     sweatshirt
    0.08
    zaam
    0.08
    actividad
    0.08
     shredded
    0.08
     jeans
    0.08
     Reject
    0.07
    Activations Density 0.001%

    No Known Activations