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. 120251
    Prev
    Next
    INDEX
    Explanations

    workplace safety

    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
     düny
    -0.08
     finance
    -0.07
     בעולם
    -0.07
     II
    -0.07
     portfolios
    -0.07
     gamble
    -0.07
     millones
    -0.07
     portfolio
    -0.07
     mailbox
    -0.07
     emprend
    -0.07
    POSITIVE LOGITS
    人员
    0.10
     whak
    0.09
     Bedien
    0.09
     谁
    0.09
    _ctl
    0.09
    igheder
    0.09
     sellele
    0.09
     Anyone
    0.08
     Personnel
    0.08
     сверху
    0.08
    Activations Density 0.039%

    No Known Activations