© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47866
    Prev
    Next
    INDEX
    Explanations

    多

    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
    很多
    -0.10
    aucoup
    -0.09
     অনেক
    -0.09
     عديدة
    -0.09
    icky
    -0.08
    	Group
    -0.08
    fox
    -0.08
     verschiedenen
    -0.08
     müxtəlif
    -0.08
    group
    -0.08
    POSITIVE LOGITS
    学
    0.11
    -eche
    0.11
    部门
    0.11
    -disciplinary
    0.11
    -source
    0.10
    方
    0.10
    点
    0.10
    赢
    0.10
     сценар
    0.10
    -functional
    0.10
    Activations Density 0.005%

    No Known Activations