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. 113080
    Prev
    Next
    INDEX
    Explanations

    pathogen-associated molecular patterns

    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
     Valladolid
    -0.09
     Espan
    -0.08
    _interp
    -0.08
    stata
    -0.08
    成绩
    -0.08
    \t
    -0.08
     Started
    -0.08
     juggling
    -0.08
    بط
    -0.08
     graphical
    -0.08
    POSITIVE LOGITS
     alde
    0.09
     detectable
    0.09
     hre
    0.09
    Plant
    0.09
    _ENTITY
    0.08
     recognizable
    0.08
     antise
    0.08
     plants
    0.08
     признаки
    0.08
    ഐ
    0.08
    Activations Density 0.002%

    No Known Activations