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. 60457
    Prev
    Next
    INDEX
    Explanations

    HTML

    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
     эсеп
    -0.09
     Sum
    -0.08
    ,sum
    -0.08
     القدم
    -0.08
    .Blue
    -0.08
    liga
    -0.08
     услов
    -0.08
     normas
    -0.08
     hizi
    -0.08
     samkvæmt
    -0.08
    POSITIVE LOGITS
     unexpectedly
    0.11
     unexpected
    0.10
    乱码
    0.10
     unintended
    0.10
    Unexpected
    0.10
     Unexpected
    0.10
     errone
    0.10
     interfering
    0.10
     mistaken
    0.09
     incorrectly
    0.09
    Activations Density 0.006%

    No Known Activations