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. 113008
    Prev
    Next
    INDEX
    Explanations

    limited

    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
     usu
    -0.08
     costum
    -0.08
    chip
    -0.08
    chg
    -0.08
     compar
    -0.08
     tiếng
    -0.07
     insight
    -0.07
     consciência
    -0.07
     Plug
    -0.07
    hol
    -0.07
    POSITIVE LOGITS
    不限
    0.08
    クト
    0.08
     beyond
    0.08
    nikov
    0.08
    �
    0.08
     symptomatic
    0.07
    verm
    0.07
     bergen
    0.07
    ต่าง
    0.07
     welcomed
    0.07
    Activations Density 0.005%

    No Known Activations