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. 11807
    Prev
    Next
    INDEX
    Explanations

    Logger

    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
     ')'
    -0.08
    keypress
    -0.08
    ages
    -0.08
     inklusive
    -0.08
     опублик
    -0.08
     investig
    -0.07
    _dn
    -0.07
     jornal
    -0.07
    anche
    -0.07
    依法
    -0.07
    POSITIVE LOGITS
     Fellowship
    0.08
     ლიდ
    0.08
    859
    0.08
    .Inventory
    0.07
    .warning
    0.07
     functionality
    0.07
    _cached
    0.07
    ичный
    0.07
    .Custom
    0.07
    Scaled
    0.07
    Activations Density 0.001%

    No Known Activations