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. 12808
    Prev
    Next
    INDEX
    Explanations

    light/photochemistry

    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
    天下
    -0.10
    家的
    -0.08
     insider
    -0.08
    人才
    -0.08
     conglomer
    -0.08
    .avg
    -0.08
    牲
    -0.08
    仓
    -0.07
     Scores
    -0.07
    삭
    -0.07
    POSITIVE LOGITS
     irradiation
    0.13
     vitamin
    0.13
     फोटो
    0.13
     фот
    0.13
     UV
    0.13
     ultraviolet
    0.13
     wavelength
    0.12
     Vitamin
    0.12
     photovoltaic
    0.12
    phot
    0.12
    Activations Density 0.014%

    No Known Activations