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. 15-RESID-POST-AA
    6. 19130
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ыя
    -0.07
     tangent
    -0.07
     Pela
    -0.07
     sumi
    -0.07
    )sender
    -0.07
     soybean
    -0.07
     Hector
    -0.07
    owitz
    -0.07
    ={[↵
    -0.07
     magnesium
    -0.07
    POSITIVE LOGITS
    _inverse
    0.09
    verting
    0.09
    inverse
    0.09
     כדי
    0.08
    ্যাল
    0.08
     Removing
    0.08
     билет
    0.08
     removing
    0.08
     ór
    0.08
    ::_
    0.08
    Activations Density 0.017%

    No Known Activations