Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 46150
    Prev
    Next
    INDEX
    Explanations

    vision and sight

    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
    /rem
    -0.08
     depot
    -0.08
    裙
    -0.08
     warehouse
    -0.07
     chair
    -0.07
     déposer
    -0.07
     weekdays
    -0.07
    .depart
    -0.07
    èv
    -0.07
    Burger
    -0.07
    POSITIVE LOGITS
     આંખ
    0.19
     binocular
    0.19
     চোখ
    0.18
     eyesight
    0.17
     आँख
    0.16
    睛
    0.16
     കണ്ണ
    0.16
     eyes
    0.16
     आंख
    0.16
     Eyes
    0.15
    Activations Density 0.129%

    No Known Activations