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

    Neuronpedia

    Jacobian LensNEW
    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. 69450
    Prev
    Next
    INDEX
    Explanations

    Spreadsheet 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
     partij
    -0.07
     hai
    -0.07
     Pat
    -0.07
     mods
    -0.07
     volledige
    -0.07
    ponenten
    -0.07
    晚
    -0.07
     Extensive
    -0.07
     marzo
    -0.07
    unan
    -0.07
    POSITIVE LOGITS
     garnered
    0.08
     deserted
    0.08
    ారి
    0.08
    _capacity
    0.08
    .spawn
    0.08
     గ్రామ
    0.08
     topp
    0.08
     hometown
    0.07
     թույլ
    0.07
     სც
    0.07
    Activations Density 0.002%

    No Known Activations