© 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. 45403
    Prev
    Next
    INDEX
    Explanations

    pattern recognition

    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
     Rigidbody
    -0.08
     Municipality
    -0.08
    IM
    -0.08
     filos
    -0.08
     Felipe
    -0.08
    IGATION
    -0.08
     pula
    -0.07
     shug
    -0.07
     tuaj
    -0.07
     Ion
    -0.07
    POSITIVE LOGITS
     patrones
    0.14
    Pattern
    0.14
    Patterns
    0.14
     patterns
    0.14
    (pattern
    0.13
     recognition
    0.13
    Recogn
    0.13
    Recognition
    0.13
     recognizing
    0.13
    .Pattern
    0.13
    Activations Density 0.013%

    No Known Activations