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. 12218
    Prev
    Next
    INDEX
    Explanations

    publication sources

    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
    reload
    -0.09
    _reload
    -0.09
     pedestrians
    -0.09
    яет
    -0.09
    ಜಾವ
    -0.08
     stimulates
    -0.08
    Reload
    -0.08
    олю
    -0.07
    stim
    -0.07
    ologisch
    -0.07
    POSITIVE LOGITS
     reputable
    0.11
    出处
    0.11
    出版社
    0.10
     prestigious
    0.10
    出版
    0.09
     mediums
    0.09
    .Source
    0.09
     මා
    0.08
     terpercaya
    0.08
    游戏平台
    0.08
    Activations Density 0.058%

    No Known Activations