© 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. 23-RESID-POST-AA
    11. 52265
    Prev
    Next
    INDEX
    Explanations

    say [the number 28]

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    -live
    -0.09
    _live
    -0.09
    -de
    -0.09
    -dé
    -0.08
     det
    -0.08
     નવ
    -0.08
     Detox
    -0.08
    avio
    -0.08
    -prov
    -0.08
     live
    -0.08
    POSITIVE LOGITS
    28
    0.34
    028
    0.21
    280
    0.13
     conforto
    0.11
     cim
    0.11
    ೃಹ
    0.10
    imid
    0.10
     imbalance
    0.10
    	im
    0.10
    underline
    0.10
    Activations Density 0.048%

    No Known Activations