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. 60705
    Prev
    Next
    INDEX
    Explanations

    debug

    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
     vấn
    -0.08
    -0.07
     clueless
    -0.07
     clothing
    -0.07
     closet
    -0.07
     sacar
    -0.07
     τρο
    -0.07
    器
    -0.07
     clo
    -0.07
     handig
    -0.07
    POSITIVE LOGITS
     iştirak
    0.09
    XPath
    0.08
    ाळ
    0.08
    тых
    0.08
     digər
    0.08
     queste
    0.08
     Rup
    0.08
    Youth
    0.08
    Italic
    0.08
     hopes
    0.08
    Activations Density 0.002%

    No Known Activations