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. 76087
    Prev
    Next
    INDEX
    Explanations

    area and volume calculations

    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
     kalan
    -0.07
     residents
    -0.07
    Residents
    -0.07
    Bibli
    -0.07
     '/
    -0.07
    _ACCESS
    -0.07
     examination
    -0.07
    _DELAY
    -0.07
     telev
    -0.07
     deliberate
    -0.06
    POSITIVE LOGITS
    badge
    0.08
     मूल
    0.08
    -trip
    0.08
    /scripts
    0.08
    ampoo
    0.08
     draag
    0.07
    spaces
    0.07
    িত্ব
    0.07
    lesson
    0.07
    _trip
    0.07
    Activations Density 0.005%

    No Known Activations