© 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. 23-RESID-POST-AA
    11. 50558
    Prev
    Next
    INDEX
    Explanations

    Rowing speed relative to water

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     वाहन
    -0.09
     വാഹന
    -0.09
     ವಾಹನ
    -0.09
    (vehicle
    -0.08
     roadway
    -0.08
    ROAD
    -0.08
     വാഹ
    -0.07
    Reflect
    -0.07
    _temp
    -0.07
     Daarom
    -0.07
    POSITIVE LOGITS
     punk
    0.09
     lutter
    0.09
     abbia
    0.09
     paulista
    0.08
     punctuation
    0.08
     points
    0.08
     الشرقية
    0.08
     minced
    0.08
     posture
    0.08
     postings
    0.08
    Activations Density 0.003%

    No Known Activations