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. 26767
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
     선언
    -0.08
    strip
    -0.07
     Alex
    -0.07
     strip
    -0.07
    ไม้
    -0.07
     Wishes
    -0.07
    Palette
    -0.07
    모
    -0.07
     인
    -0.07
     주민
    -0.07
    POSITIVE LOGITS
    网上
    0.10
    www
    0.09
     https
    0.09
    adwy
    0.08
    doi
    0.08
    网址
    0.08
     websites
    0.08
    https
    0.08
     ઓનલ
    0.08
     Всем
    0.08
    Activations Density 0.029%

    No Known Activations