© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110638
    Prev
    Next
    INDEX
    Explanations

    Sports incidents/fighting

    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
    oyo
    -0.07
     progression
    -0.07
     progres
    -0.07
     principles
    -0.07
     homeschooling
    -0.07
     principle
    -0.07
    Princip
    -0.07
     Principle
    -0.07
     mastery
    -0.07
     Mathf
    -0.07
    POSITIVE LOGITS
     árbit
    0.11
    违规
    0.11
     referee
    0.10
     controversy
    0.10
     विवाद
    0.10
     احترام
    0.09
     cleaners
    0.09
     گزارش
    0.09
    涉嫌
    0.09
     lịch
    0.09
    Activations Density 0.066%

    No Known Activations