© 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. 18018
    Prev
    Next
    INDEX
    Explanations

    --

    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
    enderror
    -0.09
    DBNull
    -0.09
    _Request
    -0.09
     ::=
    -0.09
     respectivas
    -0.09
    ادمة
    -0.09
    Terminate
    -0.08
    _putchar
    -0.08
    _Send
    -0.08
    iwill
    -0.08
    POSITIVE LOGITS
    高清
    0.10
     высокого
    0.10
     scènes
    0.10
     yüksək
    0.09
     تصوير
    0.09
     высокая
    0.09
     Scenes
    0.09
     плот
    0.09
    尺度
    0.09
     کیفیت
    0.09
    Activations Density 0.001%

    No Known Activations