© 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. 23051
    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
     Nottingham
    -0.10
    英国
    -0.10
     Hampshire
    -0.10
    法国
    -0.09
     немец
    -0.09
     Zurich
    -0.09
    £
    -0.09
     Leicester
    -0.09
     £
    -0.09
    德国
    -0.09
    POSITIVE LOGITS
     Philippine
    0.22
    菲律宾
    0.22
     Filipino
    0.22
     mga
    0.22
     Pilipinas
    0.21
     Cebu
    0.21
     Philippines
    0.20
     barang
    0.20
     菲律宾
    0.20
     bagong
    0.20
    Activations Density 0.046%

    No Known Activations