© 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. 109819
    Prev
    Next
    INDEX
    Explanations

    quaternions

    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
    Economic
    -0.10
    催
    -0.10
    Revenue
    -0.09
     admissions
    -0.09
     Admissions
    -0.09
     terrace
    -0.09
     subsidy
    -0.09
    Tier
    -0.09
    Referral
    -0.09
    College
    -0.09
    POSITIVE LOGITS
     quaternion
    0.19
     Quaternion
    0.16
    Quaternion
    0.15
     quat
    0.13
    Quat
    0.12
     rotations
    0.11
    quat
    0.11
    rotation
    0.10
     Rotation
    0.10
     вращ
    0.10
    Activations Density 0.006%

    No Known Activations