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. 49185
    Prev
    Next
    INDEX
    Explanations

    methodology

    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
     schemes
    -0.08
    left
    -0.07
    айте
    -0.07
    Ramp
    -0.07
    Tä
    -0.07
    Chef
    -0.07
    both
    -0.07
    Tau
    -0.07
    Linha
    -0.07
    рю
    -0.07
    POSITIVE LOGITS
     조사
    0.11
     നടത്തിയ
    0.10
    进行了
    0.10
     methodology
    0.09
     consulted
    0.09
     गरेको
    0.09
    调查
    0.09
     conducted
    0.09
    筛
    0.08
     করেছি
    0.08
    Activations Density 0.038%

    No Known Activations