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. 67198
    Prev
    Next
    INDEX
    Explanations

    common words

    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
     Himal
    -0.08
     DSM
    -0.07
    ausa
    -0.07
    adu
    -0.07
    nga
    -0.07
     Wahl
    -0.07
     deletes
    -0.07
     disorder
    -0.07
    	stage
    -0.07
    chir
    -0.07
    POSITIVE LOGITS
    ביע
    0.08
     ce
    0.08
     بين
    0.07
    RC
    0.07
     endian
    0.07
     بطريقة
    0.07
    中特
    0.07
     rc
    0.07
    .gre
    0.07
     св
    0.07
    Activations Density 0.189%

    No Known Activations