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. 88085
    Prev
    Next
    INDEX
    Explanations

    animal intelligence and tool use

    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
    ectors
    -0.08
    koa
    -0.08
     biraz
    -0.08
     serializers
    -0.07
    கு
    -0.07
     Пу
    -0.07
     driv
    -0.07
     io
    -0.07
     mío
    -0.07
     contributions
    -0.07
    POSITIVE LOGITS
     മനുഷ്യ
    0.09
     মানুষের
    0.09
    Unexpected
    0.08
     learned
    0.08
     আচ
    0.08
     gelernt
    0.08
    Ẹ
    0.08
     Venetian
    0.08
    Weapon
    0.08
     Learned
    0.08
    Activations Density 0.019%

    No Known Activations