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. 77308
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    Json
    -0.08
    unti
    -0.07
     Asheville
    -0.07
     Orwell
    -0.07
     tighter
    -0.07
     تھ
    -0.07
    ニュー
    -0.07
    esc
    -0.07
     ремон
    -0.07
    339
    -0.07
    POSITIVE LOGITS
     sine
    0.09
     decoder
    0.08
    olic
    0.08
    äger
    0.08
    decoder
    0.08
     grec
    0.08
     Imag
    0.08
     anim
    0.08
     Alarm
    0.08
    Imag
    0.08
    Activations Density 0.081%

    No Known Activations