© 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. 21644
    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
     considérer
    -0.10
     pratiquer
    -0.10
     considerar
    -0.09
     advocating
    -0.09
     utilisent
    -0.09
    .atguigu
    -0.09
     vergleichen
    -0.09
     olevan
    -0.09
     confirming
    -0.09
     svojo
    -0.09
    POSITIVE LOGITS
     lead
    0.14
     cause
    0.13
     affect
    0.13
     result
    0.12
    导致
    0.12
     jeopard
    0.11
     create
    0.11
     disrupt
    0.11
     worsen
    0.10
    lead
    0.10
    Activations Density 0.022%

    No Known Activations