© 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. 3-RESID-POST-AA
    11. 2500
    Prev
    Next
    INDEX
    Explanations

    origin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arena
    -0.08
     mate
    -0.07
    Descending
    -0.07
     fan
    -0.07
    eps
    -0.07
    660
    -0.07
     lap
    -0.07
    -0.07
     descending
    -0.07
     rod
    -0.07
    POSITIVE LOGITS
     regularmente
    0.08
    యం
    0.08
     Linn
    0.08
    Bul
    0.08
     quen
    0.07
    -born
    0.07
     Exhaust
    0.07
     Bab
    0.07
     Bremen
    0.07
    yard
    0.07
    Activations Density 0.007%
    No Known Activations