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. 23-RESID-POST-AA
    6. 97975
    Prev
    Next
    INDEX
    Explanations

    ру

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _instance
    -0.08
     Nes
    -0.07
     articles
    -0.07
    770
    -0.07
    rozen
    -0.07
    рон
    -0.07
     Nav
    -0.07
     compatible
    -0.07
    ীম
    -0.07
    Vu
    -0.07
    POSITIVE LOGITS
    geten
    0.09
    gey
    0.09
    ixa
    0.08
     üçün
    0.08
    ga
    0.08
     gog
    0.08
    >alert
    0.08
    geht
    0.08
     लाम
    0.07
     eerder
    0.07
    Activations Density 0.000%

    No Known Activations