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. 56165
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ,而且
    -0.08
     అనే
    -0.08
    甚至
    -0.08
     న
    -0.08
    لاب
    -0.08
     গুরুত্ব
    -0.08
    ,因此
    -0.08
    ,而
    -0.07
     chipped
    -0.07
    という
    -0.07
    POSITIVE LOGITS
     Firstly
    0.10
    Firstly
    0.09
     firstly
    0.09
     먼저
    0.09
     Suppose
    0.08
    ระบบ
    0.08
     системой
    0.08
    Elastic
    0.08
    .har
    0.08
     Elastic
    0.08
    Activations Density 0.103%

    No Known Activations