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. 44692
    Prev
    Next
    INDEX
    Explanations

    appearance/inspection

    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
     deswegen
    -0.09
     epsilon
    -0.09
     ε
    -0.08
     ensemble
    -0.08
     aza
    -0.08
    _until
    -0.08
     $.
    -0.07
    011
    -0.07
     $(".
    -0.07
    Writer
    -0.07
    POSITIVE LOGITS
     wounds
    0.10
    是否
    0.09
     सहज
    0.09
     shadows
    0.08
    社会
    0.08
     thái
    0.08
     सामाजिक
    0.08
     demeanor
    0.08
     hervor
    0.07
     是否
    0.07
    Activations Density 0.004%

    No Known Activations