© 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. 18104
    Prev
    Next
    INDEX
    Explanations

    sophisticated

    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
    十五
    -0.08
    স্থ
    -0.08
    สิบ
    -0.08
    ব্য
    -0.07
     sixty
    -0.07
     beware
    -0.07
     fifteen
    -0.07
    worthy
    -0.07
    údio
    -0.07
     Coordinates
    -0.07
    POSITIVE LOGITS
     ರೀತ
    0.11
    isticated
    0.09
    -like
    0.09
     듯
    0.09
    ’ir
    0.08
     vs
    0.08
    ate
    0.08
     棋牌
    0.08
     तरह
    0.08
     ausdr
    0.08
    Activations Density 0.004%

    No Known Activations