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. 60758
    Prev
    Next
    INDEX
    Explanations

    Carotenoids

    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
    Servico
    -0.08
     chast
    -0.08
     Inde
    -0.08
     manus
    -0.08
     ka
    -0.08
     Ministry
    -0.07
    /gtest
    -0.07
     akwụ
    -0.07
     Método
    -0.07
    િકેટ
    -0.07
    POSITIVE LOGITS
    _opt
    0.08
    690
    0.08
    δα
    0.08
    彩
    0.08
     milieu
    0.07
    .CO
    0.07
    563
    0.07
     OPS
    0.07
    Hot
    0.07
    lic
    0.07
    Activations Density 0.006%

    No Known Activations