Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 54294
    Prev
    Next
    INDEX
    Explanations

    hand

    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
     shipped
    -0.09
     Herc
    -0.08
     administrative
    -0.08
     administr
    -0.08
     metr
    -0.07
    gly
    -0.07
     shipping
    -0.07
     hér
    -0.07
     mythical
    -0.07
     warehouses
    -0.07
    POSITIVE LOGITS
     votar
    0.11
     বক্তব্য
    0.11
    .vote
    0.10
     मतदान
    0.10
     ভোট
    0.10
     ಮತ
    0.10
    讲话
    0.10
    สดงความคิดเห็น
    0.10
    Voting
    0.10
     unanimous
    0.10
    Activations Density 0.061%

    No Known Activations