© 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. 47505
    Prev
    Next
    INDEX
    Explanations

    community events and workshops

    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
     остальных
    -0.09
     demás
    -0.08
    -sized
    -0.07
    .Visit
    -0.07
     המשחק
    -0.07
    Contact
    -0.07
     Contact
    -0.07
     namely
    -0.07
     dep
    -0.07
     pinc
    -0.07
    POSITIVE LOGITS
     beispielsweise
    0.10
     régulièrement
    0.09
    例如
    0.08
     Beispiele
    0.08
    द
    0.08
    ，例如
    0.08
    甚至
    0.08
    促进
    0.08
     countless
    0.08
     Kör
    0.08
    Activations Density 0.171%

    No Known Activations