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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 76299
    Prev
    Next
    INDEX
    Explanations

    text

    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
    allan
    -0.08
    _application
    -0.08
     pell
    -0.08
     amalg
    -0.08
     힘
    -0.08
     mamá
    -0.07
     gesp
    -0.07
     isku
    -0.07
    母
    -0.07
    落实
    -0.07
    POSITIVE LOGITS
     exceed
    0.10
     surpass
    0.09
     commentary
    0.09
     dépass
    0.09
     أكبر
    0.09
     exceeded
    0.08
     exceeds
    0.08
     كبير
    0.08
     exceeding
    0.08
    Exceeded
    0.08
    Activations Density 0.001%

    No Known Activations