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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97246
    Prev
    Next
    INDEX
    Explanations

    老

    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
    lab
    -0.09
    complex
    -0.08
    t
    -0.08
    klin
    -0.08
    multip
    -0.08
    복
    -0.08
    -responsive
    -0.08
    conv
    -0.08
    pon
    -0.08
    metry
    -0.08
    POSITIVE LOGITS
    虎
    0.11
    鼠
    0.11
    字号
    0.11
    奶头
    0.10
    舗
    0.10
    鹰
    0.10
    资格
    0.10
    爷
    0.10
    旧
    0.10
    年
    0.09
    Activations Density 0.001%

    No Known Activations