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. 30495
    Prev
    Next
    INDEX
    Explanations

    Sans

    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
    鹰
    -0.08
     negativas
    -0.07
     Pearson
    -0.07
     neoliberal
    -0.07
     Greenwich
    -0.07
    ุง
    -0.07
    ทธิ
    -0.07
     republican
    -0.07
    ction
    -0.07
    akhir
    -0.07
    POSITIVE LOGITS
    ghost
    0.09
    bones
    0.09
     ghosts
    0.08
     ghost
    0.08
    /be
    0.08
     Haha
    0.07
     Ghost
    0.07
    Goto
    0.07
     সৈ
    0.07
     Bones
    0.07
    Activations Density 0.001%

    No Known Activations