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. 104043
    Prev
    Next
    INDEX
    Explanations

    deliberate practice

    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
     VAN
    -0.08
     gás
    -0.08
    holm
    -0.07
    ifornia
    -0.07
    Recipients
    -0.07
     Appliances
    -0.07
    男子
    -0.07
     বাত
    -0.07
     MENU
    -0.07
     আটক
    -0.07
    POSITIVE LOGITS
     incremental
    0.10
     lær
    0.09
     purposeful
    0.09
    structured
    0.09
     structured
    0.08
     targeted
    0.08
     luyện
    0.08
    practice
    0.08
     practice
    0.08
    JV
    0.08
    Activations Density 0.010%

    No Known Activations