© 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. 19458
    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
     उत्पादन
    -0.10
     спеці
    -0.09
    .home
    -0.08
     spécialement
    -0.08
    .production
    -0.08
     proizvod
    -0.08
     zusammen
    -0.08
     ઉત્પાદન
    -0.08
     graduates
    -0.08
     produz
    -0.08
    POSITIVE LOGITS
     rares
    0.08
    flora
    0.08
    168
    0.08
     rare
    0.07
     poucos
    0.07
     pocos
    0.07
    _zero
    0.07
    Zero
    0.07
     sparse
    0.07
    105
    0.07
    Activations Density 0.001%

    No Known Activations