© 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. 99267
    Prev
    Next
    INDEX
    Explanations

    word tables

    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
     התמ
    -0.08
     presentación
    -0.08
     \(
    -0.08
     말을
    -0.08
     Coaches
    -0.08
     Präsent
    -0.08
    .jfree
    -0.07
     USS
    -0.07
     Tier
    -0.07
    .fxml
    -0.07
    POSITIVE LOGITS
     parenting
    0.08
     prop
    0.07
     sequ
    0.07
     campground
    0.07
     attrib
    0.07
     blocker
    0.07
     Parenting
    0.07
     sequencing
    0.07
    CM
    0.07
     continu
    0.07
    Activations Density 0.001%

    No Known Activations