© 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. 71487
    Prev
    Next
    INDEX
    Explanations

    geometry circle problems

    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
    Not in Any Lists

    No Comments

    Negative Logits
     occasional
    -0.09
     Unt
    -0.08
     cuyos
    -0.08
    urder
    -0.08
    မ
    -0.08
     hidup
    -0.07
     hail
    -0.07
    hail
    -0.07
    =set
    -0.07
     câu
    -0.07
    POSITIVE LOGITS
    吻
    0.08
     infinit
    0.08
    ‌ش
    0.08
     ખાતે
    0.08
    銀
    0.07
    位置
    0.07
    Esse
    0.07
     Neptune
    0.07
    银
    0.07
     rim
    0.07
    Activations Density 0.025%

    No Known Activations