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. 11874
    Prev
    Next
    INDEX
    Explanations

    informal text/emphasis

    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
     really
    -0.08
     achar
    -0.07
     tutt
    -0.07
     Realtors
    -0.07
     subito
    -0.07
     ka
    -0.07
     Cad
    -0.07
     percentages
    -0.07
    **↵↵
    -0.07
     percentile
    -0.07
    POSITIVE LOGITS
    THIS
    0.09
    NEW
    0.08
    欺
    0.08
    =}
    0.08
    thus
    0.08
     Fake
    0.08
    _INSTANCE
    0.08
    APPLICATION
    0.08
    _application
    0.08
    Included
    0.08
    Activations Density 0.004%

    No Known Activations