© 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. 99858
    Prev
    Next
    INDEX
    Explanations

    Gradle wrapper

    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
    ী
    -0.08
     satisfied
    -0.07
    க்க
    -0.07
    ali
    -0.07
    性的
    -0.07
    ப்ப
    -0.07
     tiên
    -0.07
     condition
    -0.07
     culinary
    -0.07
     deepest
    -0.07
    POSITIVE LOGITS
     三
    0.08
    紹
    0.08
     teléfonos
    0.08
     Formular
    0.08
     Nal
    0.08
     Thousand
    0.08
     overst
    0.08
     Drei
    0.07
     Neces
    0.07
     variedad
    0.07
    Activations Density 0.000%

    No Known Activations