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. 106309
    Prev
    Next
    INDEX
    Explanations

    rabbits and other animals

    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
     determinadas
    -0.08
     jitter
    -0.08
     질
    -0.08
    alia
    -0.08
     cheap
    -0.08
    irai
    -0.07
     ldc
    -0.07
    .target
    -0.07
     joga
    -0.07
    );
    ↵/
    -0.07
    POSITIVE LOGITS
     девушка
    0.09
     девуш
    0.08
    ový
    0.08
    女孩
    0.08
    女子
    0.08
     ছেলে
    0.08
     Pins
    0.08
     लड़की
    0.08
    姑娘
    0.08
     Mädchen
    0.08
    Activations Density 0.037%

    No Known Activations