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. 11620
    Prev
    Next
    INDEX
    Explanations

    主题

    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
     singer
    -0.08
    ryer
    -0.07
    一期
    -0.07
     socks
    -0.07
     needy
    -0.07
     releasing
    -0.07
    iams
    -0.07
    �
    -0.07
    URA
    -0.07
    ()/
    -0.07
    POSITIVE LOGITS
     제목
    0.08
     عشر
    0.08
     horrific
    0.07
    -chave
    0.07
     רב
    0.07
     Hog
    0.07
     слав
    0.07
     свид
    0.07
     гру
    0.07
     Прав
    0.07
    Activations Density 0.002%

    No Known Activations