Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 59403
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Connecticut
    -0.10
     Yankees
    -0.10
     hurricane
    -0.10
     Roosevelt
    -0.10
     Yankee
    -0.09
    storms
    -0.09
     الأمريكي
    -0.09
    SMTP
    -0.09
    .smtp
    -0.09
     Verizon
    -0.09
    POSITIVE LOGITS
    .vue
    0.18
    /vue
    0.17
    Vue
    0.17
     Vue
    0.16
    (Vue
    0.16
    vue
    0.16
     vue
    0.16
    _vue
    0.15
     lodash
    0.11
    Webpack
    0.11
    Activations Density 0.035%

    No Known Activations