© 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. 109913
    Prev
    Next
    INDEX
    Explanations

    radioactive

    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
    ubahan
    -0.08
    த்திய
    -0.07
    Cha
    -0.07
    ambles
    -0.07
    යක
    -0.07
     수
    -0.07
    Ip
    -0.07
    Parce
    -0.07
    جام
    -0.07
     ante
    -0.07
    POSITIVE LOGITS
     substances
    0.11
     ν
    0.09
     вещества
    0.09
     nu
    0.09
     stains
    0.09
     stoffen
    0.08
    zne
    0.08
     zir
    0.08
     nr
    0.08
    	alpha
    0.08
    Activations Density 0.003%

    No Known Activations