© 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. 78840
    Prev
    Next
    INDEX
    Explanations

    >

    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
     heaters
    -0.08
    ,out
    -0.08
     wij
    -0.07
     finalize
    -0.07
     Lore
    -0.07
     Germans
    -0.07
    >end
    -0.07
     говорят
    -0.07
     MAY
    -0.07
    [](
    -0.07
    POSITIVE LOGITS
     disappointment
    0.08
     disappoint
    0.08
     trough
    0.08
     consolation
    0.08
    hill
    0.07
    败
    0.07
    _old
    0.07
    န
    0.07
     despair
    0.07
     unfortunate
    0.07
    Activations Density 0.006%

    No Known Activations