© 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. 21302
    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
     bepaalde
    -0.09
     שאנחנו
    -0.08
     specifies
    -0.08
     그런데
    -0.08
     bestimmte
    -0.08
    是什么意思
    -0.08
     ozna
    -0.07
     次
    -0.07
    인데
    -0.07
     ซึ่ง
    -0.07
    POSITIVE LOGITS
     still
    0.16
    仍
    0.15
     yine
    0.14
     Still
    0.14
    Still
    0.14
     comunque
    0.13
     STILL
    0.13
    still
    0.13
     again
    0.12
     because
    0.12
    Activations Density 0.040%

    No Known Activations