© 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. 108723
    Prev
    Next
    INDEX
    Explanations

    dramatic irony

    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
    anish
    -0.08
    obyl
    -0.08
     Domin
    -0.08
     dominate
    -0.08
    iren
    -0.07
    丨
    -0.07
     dominance
    -0.07
     wandeling
    -0.07
    iritual
    -0.07
     dominates
    -0.07
    POSITIVE LOGITS
    ാക
    0.10
     antagon
    0.09
    ാക്
    0.08
     expectativa
    0.08
     anticipation
    0.08
     sarcast
    0.08
     contrasted
    0.08
    ിന്ദ
    0.08
     tiet
    0.08
     противоп
    0.08
    Activations Density 0.005%

    No Known Activations