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

    Neuronpedia

    Jacobian LensNEW
    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. 49405
    Prev
    Next
    INDEX
    Explanations

    Food related (Chinese)

    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
    יצה
    -0.08
    ädt
    -0.08
    -0.08
    ding
    -0.08
    нда
    -0.08
    יץ
    -0.08
     Ced
    -0.08
    TING
    -0.07
     exert
    -0.07
     гран
    -0.07
    POSITIVE LOGITS
    單
    0.14
    �
    0.13
    谱
    0.13
    系
    0.11
    鸟
    0.11
    品
    0.11
    �
    0.11
    单位
    0.09
    鳥
    0.09
    式
    0.09
    Activations Density 0.001%
    No Known Activations