© 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. 11-RESID-POST-AA
    11. 129264
    Prev
    Next
    INDEX
    Explanations

    在

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overwrite
    -0.08
     पस
    -0.08
     값을
    -0.08
     astr
    -0.08
     lief
    -0.08
     тег
    -0.08
    ્ષ
    -0.07
     charm
    -0.07
    osição
    -0.07
     lié
    -0.07
    POSITIVE LOGITS
    近年来
    0.13
    如今
    0.12
    对于
    0.12
    不仅
    0.11
    另一方面
    0.11
    与此同时
    0.10
    数据显示
    0.10
    而言
    0.10
    过程中
    0.10
    首先
    0.10
    Activations Density 0.044%

    No Known Activations