© 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. 21174
    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
     décennies
    -0.11
     Hundreds
    -0.11
     hundreds
    -0.10
     treinta
    -0.10
     Thousands
    -0.09
     thousands
    -0.09
     decades
    -0.09
     tientallen
    -0.09
     cientos
    -0.09
     dozens
    -0.09
    POSITIVE LOGITS
     midpoint
    0.10
     mid
    0.10
     મધ
    0.10
    mid
    0.10
    Mid
    0.10
     midway
    0.10
    _mid
    0.09
    (mid
    0.09
     орта
    0.09
    年底
    0.09
    Activations Density 0.027%

    No Known Activations