© 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. 103223
    Prev
    Next
    INDEX
    Explanations

    self

    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
    	of
    -0.09
    IBUTES
    -0.09
    ថ្ងៃទី
    -0.09
     weib
    -0.09
    重庆时时彩
    -0.09
     Webcam
    -0.09
    双色
    -0.09
    ថ្មី
    -0.09
    IZES
    -0.09
     վերադարձ
    -0.09
    POSITIVE LOGITS
    -esteem
    0.20
    -ident
    0.16
    -awareness
    0.16
    -confidence
    0.16
    -
    0.15
    ‑
    0.14
    -love
    0.14
    -ad
    0.13
    -re
    0.13
    -conscious
    0.13
    Activations Density 0.012%

    No Known Activations