© 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. 11-RESID-POST-AA
    11. 109957
    Prev
    Next
    INDEX
    Explanations

    Signatures or approval

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Cipher
    -0.08
    Hasher
    -0.08
    tons
    -0.07
     속
    -0.07
    세
    -0.07
    。でも
    -0.07
    勢
    -0.07
    281
    -0.07
     Fortunately
    -0.07
    ther
    -0.07
    POSITIVE LOGITS
    确认
    0.11
    认可
    0.11
     സ്ഥിരീകര
    0.10
    approve
    0.10
     approve
    0.10
     approving
    0.10
     approval
    0.10
     aprobar
    0.10
    inisek
    0.09
     verify
    0.09
    Activations Density 0.014%

    No Known Activations