Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49139
    Prev
    Next
    INDEX
    Explanations

    program

    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
    heng
    -0.08
     ope
    -0.07
    充值
    -0.07
    事项
    -0.07
    ahlen
    -0.07
     junto
    -0.07
    输入
    -0.07
     输入
    -0.07
     hyp
    -0.07
    交
    -0.07
    POSITIVE LOGITS
    (State
    0.08
     mediated
    0.08
    (World
    0.08
    ઈ
    0.08
    ઇ
    0.08
     Ministry
    0.08
    _Tis
    0.07
    (Mockito
    0.07
    -mediated
    0.07
    ுகின்ற
    0.07
    Activations Density 0.068%

    No Known Activations