© 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. 19-RESID-POST-AA
    11. 22543
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     size
    -0.08
     sizing
    -0.08
     آور
    -0.07
    -sized
    -0.07
     tamaño
    -0.07
     coloration
    -0.07
    -colored
    -0.07
     seating
    -0.07
    尺寸
    -0.07
    -size
    -0.07
    POSITIVE LOGITS
     Euros
    0.09
     euros
    0.09
     Encourage
    0.08
      
    0.08
    东北
    0.08
     >>↵
    0.08
     *(
    0.08
     *((
    0.08
     靖
    0.08
     Advis
    0.08
    Activations Density 0.002%

    No Known Activations