© 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. 18128
    Prev
    Next
    INDEX
    Explanations

    ten

    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
    Grpc
    -0.08
    _shader
    -0.08
    胞
    -0.08
     Shader
    -0.07
    勇
    -0.07
     Hamilton
    -0.07
    oodle
    -0.07
     husband's
    -0.07
     Mittwoch
    -0.07
     persönliche
    -0.07
    POSITIVE LOGITS
     деся
    0.20
     দশ
    0.19
     दस
    0.19
     عشرة
    0.18
     diez
    0.18
     десят
    0.17
     decade
    0.17
     deset
    0.16
     ten
    0.16
     zehn
    0.16
    Activations Density 0.055%

    No Known Activations