© 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 EvalsExportsinterp-engineNEWAPI 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. 111014
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
     piracy
    -0.08
     termites
    -0.08
    政
    -0.08
    /poly
    -0.08
     religions
    -0.08
     Parsons
    -0.08
     Roads
    -0.08
    /block
    -0.08
     collectibles
    -0.08
    /order
    -0.08
    POSITIVE LOGITS
     pediatric
    0.13
    患者
    0.12
     દર્દ
    0.12
     Pediatric
    0.12
     пациент
    0.12
     Patienten
    0.12
    Patient
    0.12
     मरीज
    0.12
    医生
    0.12
     patients
    0.11
    Activations Density 0.004%

    No Known Activations