© 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. 68178
    Prev
    Next
    INDEX
    Explanations

    "I found this on"

    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
     advantageous
    -0.09
     stages
    -0.08
    ayon
    -0.08
    AJOR
    -0.07
     duly
    -0.07
     prépare
    -0.07
     jud
    -0.07
    ื่อน
    -0.07
     ymchw
    -0.07
     stade
    -0.07
    POSITIVE LOGITS
     FIFO
    0.08
     Ded
    0.08
    _fifo
    0.08
     Hills
    0.07
    (paren
    0.07
     Fondo
    0.07
     Milli
    0.07
     Sac
    0.07
    Ded
    0.07
     Tril
    0.07
    Activations Density 0.002%

    No Known Activations