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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 30672
    Prev
    Next
    INDEX
    Explanations

    characters encoding

    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
     самостоятель
    -0.09
     olje
    -0.08
     disciplined
    -0.08
     Darcy
    -0.08
    waters
    -0.08
     Gif
    -0.08
     перел
    -0.08
     oil
    -0.08
    gas
    -0.08
     газ
    -0.08
    POSITIVE LOGITS
    、大
    0.08
     નામ
    0.08
    剧情
    0.08
    /book
    0.08
     പേര
    0.08
     dl
    0.08
     वाले
    0.08
     carpeta
    0.08
    .filename
    0.08
     בשם
    0.07
    Activations Density 0.003%

    No Known Activations