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. 54023
    Prev
    Next
    INDEX
    Explanations

    task completion/work problems

    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
     microscope
    -0.07
     brass
    -0.07
     badminton
    -0.07
     നേത
    -0.07
     aerobic
    -0.07
     concussion
    -0.07
     MAS
    -0.07
    麦
    -0.07
     Bray
    -0.07
    preced
    -0.07
    POSITIVE LOGITS
     완료
    0.13
    .finished
    0.13
    完成
    0.12
     atteindre
    0.12
    finished
    0.11
     lõp
    0.11
    累计
    0.11
    达到
    0.11
     finale
    0.11
     lõpet
    0.11
    Activations Density 0.067%

    No Known Activations