© 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. 23-RESID-POST-AA
    11. 52229
    Prev
    Next
    INDEX
    Explanations

    e

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    向
    -0.08
     desk
    -0.08
    打
    -0.08
    況
    -0.08
     launch
    -0.07
     क्लिक
    -0.07
     architecture
    -0.07
    èvement
    -0.07
     או
    -0.07
    ğine
    -0.07
    POSITIVE LOGITS
    Tha
    0.11
    anyu
    0.10
    astern
    0.10
    Od
    0.09
    QString
    0.09
     Macedonia
    0.09
    Za
    0.09
    Songs
    0.09
    Ib
    0.09
    czema
    0.09
    Activations Density 0.018%

    No Known Activations