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. 19054
    Prev
    Next
    INDEX
    Explanations

    circle equations

    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
     ratios
    -0.10
    Ratio
    -0.09
    _RATIO
    -0.09
     Ratio
    -0.09
     ocas
    -0.08
    െങ്ക
    -0.08
     entertaining
    -0.08
    不能
    -0.08
     entertain
    -0.08
     Rat
    -0.08
    POSITIVE LOGITS
    decoded
    0.10
    .decode
    0.09
     decoded
    0.09
     decipher
    0.09
    центр
    0.09
     CGRect
    0.09
    _center
    0.08
    parameters
    0.08
     extracting
    0.08
     Standort
    0.08
    Activations Density 0.024%

    No Known Activations