© 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. 45284
    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
    쉬
    -0.08
     tourn
    -0.08
     tə
    -0.08
    әнә
    -0.08
     epoxy
    -0.08
    jor
    -0.07
     Joi
    -0.07
     quảng
    -0.07
    �
    -0.07
     harr
    -0.07
    POSITIVE LOGITS
     isit
    0.08
     flaw
    0.07
     procura
    0.07
     knocks
    0.07
     supermarket
    0.07
     grocery
    0.07
    Checks
    0.07
     kader
    0.07
     Basketball
    0.07
     restroom
    0.07
    Activations Density 0.000%

    No Known Activations