© 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. 44622
    Prev
    Next
    INDEX
    Explanations

    Code, function calls

    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
    主义
    -0.08
    .pic
    -0.08
     Sha
    -0.07
    _validator
    -0.07
    (prop
    -0.07
    IA
    -0.07
     rewards
    -0.07
    iação
    -0.07
     tenaga
    -0.07
     teknoloj
    -0.07
    POSITIVE LOGITS
     deletion
    0.09
    ne
    0.08
     neph
    0.08
     betekenis
    0.08
    stop
    0.07
     deleted
    0.07
     löschen
    0.07
     Deleted
    0.07
    delete
    0.07
    .delete
    0.07
    Activations Density 0.001%

    No Known Activations