© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13180
    Prev
    Next
    INDEX
    Explanations

    entro

    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
     Nis
    -0.08
     Cooperation
    -0.08
     NIC
    -0.08
    aes
    -0.07
    司机
    -0.07
     Disorders
    -0.07
     Ste
    -0.07
     disorders
    -0.07
     файл
    -0.07
     transactions
    -0.07
    POSITIVE LOGITS
    hrá
    0.07
    цы
    0.07
     dazu
    0.07
    :type
    0.07
    OH
    0.07
    Hans
    0.07
     uplift
    0.07
    brief
    0.07
    placeholder
    0.07
    rece
    0.07
    Activations Density 0.001%

    No Known Activations