© 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 EvalsExportsAPI 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. 112351
    Prev
    Next
    INDEX
    Explanations

    real-time

    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
    伦理
    -0.08
    োষ
    -0.08
    _Email
    -0.08
    Destructor
    -0.08
     morally
    -0.08
     Intended
    -0.08
     morals
    -0.08
     unethical
    -0.08
    Logical
    -0.08
     Chiropractic
    -0.08
    POSITIVE LOGITS
    实时
    0.10
     predicting
    0.09
     planning
    0.09
     predicts
    0.08
     horaires
    0.08
     predictive
    0.08
     horarios
    0.08
    查询
    0.08
    规划
    0.08
     realtime
    0.08
    Activations Density 0.015%

    No Known Activations