© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22976
    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
    Negative Logits
     waxaana
    -0.11
     meestal
    -0.09
     cómo
    -0.09
     لأنها
    -0.09
     how
    -0.09
     لأنه
    -0.08
     عادة
    -0.08
     jechuun
    -0.08
    .These
    -0.08
     وكيف
    -0.08
    POSITIVE LOGITS
     equals
    0.16
     exceeds
    0.15
     satisfies
    0.13
     is
    0.12
     achieves
    0.12
     becomes
    0.11
     beträgt
    0.11
    equals
    0.11
     remains
    0.11
    有所
    0.11
    Activations Density 0.141%

    No Known Activations