Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 58575
    Prev
    Next
    INDEX
    Explanations

    wind

    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
     deserve
    -0.08
    idunt
    -0.08
     kres
    -0.08
     trid
    -0.08
     dimensional
    -0.08
     necessitat
    -0.08
    ixture
    -0.07
    uzima
    -0.07
     दस्त
    -0.07
     populated
    -0.07
    POSITIVE LOGITS
     Renewable
    0.11
     renewable
    0.11
     الشمس
    0.09
     thiên
    0.09
     erne
    0.08
     sunlight
    0.08
     wind
    0.08
     solaire
    0.08
     солне
    0.08
    太阳
    0.08
    Activations Density 0.019%

    No Known Activations