© 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. 19488
    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
     trabalhar
    -0.08
    .work
    -0.07
    -Port
    -0.07
    -0.07
     Lisbon
    -0.07
    				
    -0.07
     để
    -0.07
    ли
    -0.07
     employ
    -0.07
     dismiss
    -0.07
    POSITIVE LOGITS
     other's
    0.09
     Oo
    0.08
     frosting
    0.08
     বন
    0.08
     Oosten
    0.08
     Contrary
    0.08
    awas
    0.08
     gewann
    0.08
    uwur
    0.08
    meye
    0.08
    Activations Density 0.001%
    No Known Activations