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. 56126
    Prev
    Next
    INDEX
    Explanations

    Chinese/Indian companies

    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
    stash
    -0.09
     stash
    -0.08
    -equiv
    -0.08
    nullptr
    -0.08
     공식
    -0.08
     Albania
    -0.08
     accession
    -0.08
    的网址
    -0.08
    虐
    -0.08
    uales
    -0.08
    POSITIVE LOGITS
     roofing
    0.09
     Motor
    0.08
     et
    0.08
     Development
    0.08
     glass
    0.07
    Development
    0.07
     গাড়
    0.07
    玻
    0.07
     موتور
    0.07
    Motor
    0.07
    Activations Density 0.018%

    No Known Activations