© 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. 11-RESID-POST-AA
    11. 109863
    Prev
    Next
    INDEX
    Explanations

    Zeus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     سکتی
    -0.08
     infest
    -0.08
     wiem
    -0.08
     exh
    -0.08
    cry
    -0.08
     raste
    -0.07
     maig
    -0.07
     downloaded
    -0.07
     walkway
    -0.07
     haunting
    -0.07
    POSITIVE LOGITS
    ole
    0.08
     hor
    0.08
    CC
    0.08
    ته
    0.08
     DOC
    0.07
     nytt
    0.07
    ouse
    0.07
     amarillo
    0.07
    主
    0.07
     utama
    0.07
    Activations Density 0.004%

    No Known Activations