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. 7-RESID-POST-AA
    6. 1924
    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_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     graduate
    -0.09
    edf
    -0.08
    poi
    -0.07
    �
    -0.07
     Ellen
    -0.07
    -pro
    -0.07
    EDF
    -0.07
    pog
    -0.07
    醒
    -0.07
    SEG
    -0.07
    POSITIVE LOGITS
    .crm
    0.08
     দ্বারা
    0.08
     đấu
    0.08
    888
    0.08
    arehouse
    0.07
     العامل
    0.07
    402
    0.07
    ברים
    0.07
     Economist
    0.07
     แม
    0.07
    Activations Density 0.003%

    No Known Activations