© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 16515
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मैं
    -0.08
     लेखक
    -0.07
    """↵
    -0.07
    .foo
    -0.07
     class
    -0.07
    ">↵
    -0.07
     relates
    -0.07
     author
    -0.07
     클래스
    -0.07
     ">↵
    -0.07
    POSITIVE LOGITS
     Surprisingly
    0.15
     surprisingly
    0.14
     paradox
    0.14
     ironically
    0.13
     strangely
    0.11
     наоборот
    0.11
     обратно
    0.11
     меньше
    0.10
     despite
    0.10
     رغم
    0.10
    Activations Density 0.091%

    No Known Activations