© 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. 95888
    Prev
    Next
    INDEX
    Explanations

    okay

    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
     miedo
    -0.07
     delo
    -0.07
     dile
    -0.07
     Andrés
    -0.07
     zuvor
    -0.07
    忘
    -0.07
     famosos
    -0.07
     infatti
    -0.07
     inaccessible
    -0.07
    汁
    -0.07
    POSITIVE LOGITS
     satisfactory
    0.13
    不错
    0.13
     respectable
    0.13
     decent
    0.10
     adequ
    0.10
     khá
    0.10
    adequ
    0.10
     adequate
    0.10
     acceptable
    0.10
     mediocre
    0.10
    Activations Density 0.070%

    No Known Activations