© 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. 20961
    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
     previously
    -0.08
    071
    -0.08
     at
    -0.08
     that's
    -0.08
    011
    -0.07
     tại
    -0.07
     beforehand
    -0.07
     wcześniej
    -0.07
    备注
    -0.07
    072
    -0.07
    POSITIVE LOGITS
     setiap
    0.18
     every
    0.17
     varje
    0.17
     fiecare
    0.17
     mỗi
    0.16
     cada
    0.16
    每
    0.16
     chaque
    0.16
     zunehm
    0.15
     દરેક
    0.15
    Activations Density 0.020%

    No Known Activations