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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 103410
    Prev
    Next
    INDEX
    Explanations

    ‑

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    纪律
    -0.09
     aprendizaje
    -0.09
    elajaran
    -0.08
     offseason
    -0.08
     reminding
    -0.08
     enforced
    -0.08
     probation
    -0.08
     생활
    -0.08
     learning
    -0.08
    提醒
    -0.08
    POSITIVE LOGITS
     trainers
    0.17
     trainer
    0.17
     Trainers
    0.15
     Trainer
    0.15
     trener
    0.14
    教师
    0.14
     facilitator
    0.14
    Trainer
    0.13
     ஆசிரிய
    0.13
    Train
    0.13
    Activations Density 0.010%

    No Known Activations