© 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. 71758
    Prev
    Next
    INDEX
    Explanations

    /

    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
    仍
    -0.08
    Chrom
    -0.08
     və
    -0.07
     dese
    -0.07
     Derr
    -0.07
    Dese
    -0.07
    -dropdown
    -0.07
    Invalidate
    -0.07
     Chrom
    -0.07
     stále
    -0.07
    POSITIVE LOGITS
     множ
    0.08
     multiplication
    0.08
     rowing
    0.07
     conducta
    0.07
    594
    0.07
    476
    0.07
     жилья
    0.07
     rows
    0.07
     colonies
    0.07
     obere
    0.07
    Activations Density 0.002%

    No Known Activations