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. 12692
    Prev
    Next
    INDEX
    Explanations

    mean

    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
     Exp
    -0.08
     freq
    -0.07
    -exp
    -0.07
     pum
    -0.07
    uel
    -0.07
    Expand
    -0.07
    Spent
    -0.07
     fmt
    -0.07
     Img
    -0.07
     Wirtschafts
    -0.07
    POSITIVE LOGITS
     tooth
    0.09
     Tooth
    0.09
     tales
    0.08
     lurking
    0.08
    玩
    0.08
     excuses
    0.07
     crafty
    0.07
     mile
    0.07
     murder
    0.07
    꿈
    0.07
    Activations Density 0.009%

    No Known Activations