© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68321
    Prev
    Next
    INDEX
    Explanations

    Math word problems

    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
     PROF
    -0.08
    blu
    -0.08
    irl
    -0.07
    Tint
    -0.07
     BUY
    -0.07
     印尼
    -0.07
    BUY
    -0.07
    _buy
    -0.07
     Dabei
    -0.07
    利润
    -0.07
    POSITIVE LOGITS
     inclusion
    0.09
     Seminary
    0.08
     cameo
    0.08
     electorate
    0.08
     Agenda
    0.08
    clus
    0.08
    Toggle
    0.07
     conjunction
    0.07
    -defined
    0.07
     orchestra
    0.07
    Activations Density 0.010%

    No Known Activations