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. 102831
    Prev
    Next
    INDEX
    Explanations

    .ass

    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
    几年
    -0.09
    (PR
    -0.09
    (PRO
    -0.08
    近年来
    -0.08
     buitenland
    -0.08
     neighborhood
    -0.08
     almeno
    -0.08
     anf
    -0.08
    前年
    -0.08
    一本
    -0.08
    POSITIVE LOGITS
    md
    0.09
     mot
    0.08
    stead
    0.07
    ama
    0.07
    ครับ
    0.07
     бе
    0.07
    fel
    0.07
    踏
    0.07
    Thinking
    0.07
    play
    0.07
    Activations Density 0.002%

    No Known Activations