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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 94881
    Prev
    Next
    INDEX
    Explanations

    parfait

    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
     Macbeth
    -0.08
     diplom
    -0.08
     sails
    -0.07
     surgeries
    -0.07
     Vr
    -0.07
     negoc
    -0.07
     war
    -0.07
     Welding
    -0.07
     дипломат
    -0.07
     guerre
    -0.07
    POSITIVE LOGITS
     parfait
    0.10
     yogurt
    0.09
     trendy
    0.09
     تناول
    0.08
     chia
    0.08
    .poster
    0.08
     podcast
    0.08
     yoghurt
    0.08
    Expandable
    0.08
     jsonify
    0.08
    Activations Density 0.007%

    No Known Activations