© 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. 22639
    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
    。那么
    -0.09
    是什么意思
    -0.09
     האם
    -0.08
     כלומר
    -0.08
     Verdict
    -0.08
     означает
    -0.08
     Interesting
    -0.08
    summary
    -0.08
     Interestingly
    -0.08
    answered
    -0.08
    POSITIVE LOGITS
    We'll
    0.16
    Unfortunately
    0.15
     We'll
    0.14
     we'll
    0.14
     Unfortunately
    0.13
     devront
    0.13
     though
    0.13
    I'll
    0.13
     I'll
    0.13
     podamos
    0.12
    Activations Density 0.054%

    No Known Activations