© 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. 94546
    Prev
    Next
    INDEX
    Explanations

    to

    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
     ومت
    -0.08
    Chron
    -0.07
    Christ
    -0.07
    -0.07
     order
    -0.07
    packer
    -0.07
    endamento
    -0.07
     serre
    -0.07
    _ORDER
    -0.07
     eder
    -0.07
    POSITIVE LOGITS
     işe
    0.09
     месту
    0.09
    త్
    0.08
     confronting
    0.08
    ാടനം
    0.08
     gan
    0.08
     делу
    0.08
     Alltag
    0.08
     gad
    0.08
     usos
    0.08
    Activations Density 0.013%
    No Known Activations