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. 49104
    Prev
    Next
    INDEX
    Explanations

    French programming documentation

    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
     ulang
    -0.08
    Mort
    -0.07
    /sdk
    -0.07
    ikum
    -0.07
    iate
    -0.07
    CTA
    -0.07
    /root
    -0.07
    Qualifier
    -0.07
    Apartment
    -0.07
    _Header
    -0.07
    POSITIVE LOGITS
     gist
    0.08
    জন
    0.08
     때
    0.08
     Ét
    0.08
     Ivan
    0.07
    ben
    0.07
    ៖
    0.07
    адам
    0.07
    -ime
    0.07
     vậy
    0.07
    Activations Density 0.011%

    No Known Activations