© 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. 23-RESID-POST-AA
    11. 6577
    Prev
    Next
    INDEX
    Explanations

    say "Research"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enery
    -0.10
    _DIRECTION
    -0.08
     됩니다
    -0.08
     attractions
    -0.08
     بھ
    -0.08
     ظروف
    -0.08
    -direction
    -0.08
     دوري
    -0.08
     vyb
    -0.08
     المجالات
    -0.08
    POSITIVE LOGITS
     uuring
    0.15
     study
    0.14
     estudo
    0.14
     даслед
    0.14
    研究
    0.13
     researchers
    0.13
     polling
    0.13
    调查
    0.13
     Study
    0.13
     Research
    0.13
    Activations Density 0.018%

    No Known Activations