© 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. 17949
    Prev
    Next
    INDEX
    Explanations

    too

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     daha
    -0.14
     보다
    -0.14
     আরও
    -0.12
     더욱
    -0.12
     lebih
    -0.12
    より
    -0.12
     更
    -0.12
     Daha
    -0.11
     ضرورة
    -0.11
     bättre
    -0.10
    POSITIVE LOGITS
     much
    0.11
    cribed
    0.11
     many
    0.10
     localized
    0.10
     reliant
    0.09
     few
    0.09
     reminiscent
    0.09
    ому
    0.09
     similar
    0.09
     telling
    0.08
    Activations Density 0.011%

    No Known Activations