© 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. 15-RESID-POST-AA
    11. 16691
    Prev
    Next
    INDEX
    Explanations

    "correct" in other languages

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kriterien
    -0.08
     ignore
    -0.08
    .criteria
    -0.07
     premise
    -0.07
    entlichen
    -0.07
     supervisors
    -0.07
     freelancers
    -0.07
     putea
    -0.07
     skips
    -0.07
    ”;
    -0.07
    POSITIVE LOGITS
    正确
    0.09
     правиль
    0.09
     correcta
    0.09
    पा
    0.09
     doğru
    0.08
     richtige
    0.08
     humane
    0.08
    वाही
    0.08
    ighteous
    0.08
     सही
    0.08
    Activations Density 0.015%

    No Known Activations