© 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 EvalsExportsAPI 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. 20785
    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
     განსაკუთრებით
    -0.09
    სპ
    -0.09
    რას
    -0.09
     განსაკუთრ
    -0.09
     հատկապես
    -0.09
    ციის
    -0.09
     trainingen
    -0.09
    ხმარ
    -0.09
    .training
    -0.09
    EDBACK
    -0.09
    POSITIVE LOGITS
     utvik
    0.09
     utveck
    0.09
     개발
    0.08
     разработ
    0.08
     desenvolvimento
    0.08
    developer
    0.08
     desenvolver
    0.08
     development
    0.08
     desenvol
    0.08
     udvik
    0.08
    Activations Density 0.004%

    No Known Activations