© 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. 44330
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     skyscr
    -0.08
     اتحاد
    -0.08
    联盟
    -0.08
    stairs
    -0.08
     متحد
    -0.08
     联
    -0.07
     physic
    -0.07
     கூட்ட
    -0.07
     Gift
    -0.07
     Sachs
    -0.07
    POSITIVE LOGITS
     判断
    0.12
     판단
    0.11
    判断
    0.11
    Classification
    0.10
     classified
    0.10
     classify
    0.10
     categorized
    0.10
    Classifier
    0.10
     classifiers
    0.09
    分類
    0.09
    Activations Density 0.018%

    No Known Activations