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. 112107
    Prev
    Next
    INDEX
    Explanations

    random number generation, bias

    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
    ров
    -0.08
     verfolgen
    -0.08
     famous
    -0.07
     теп
    -0.07
    ?',↵
    -0.07
    هنية
    -0.07
    Tabs
    -0.07
    cher
    -0.07
     management
    -0.07
    лей
    -0.07
    POSITIVE LOGITS
     rejection
    0.10
     Reject
    0.10
     reject
    0.09
     veto
    0.09
     Bias
    0.09
     rejected
    0.09
     Efficient
    0.09
     rejecting
    0.08
     rejects
    0.08
     >",
    0.08
    Activations Density 0.004%

    No Known Activations