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

    Neuronpedia

    APICircuit 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. 30592
    Prev
    Next
    INDEX
    Explanations

    questions

    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
     ĝ
    -0.08
    'appr
    -0.08
     répond
    -0.08
     supprim
    -0.08
     appr
    -0.08
    tent
    -0.07
     poursu
    -0.07
    immut
    -0.07
    /API
    -0.07
    ooj
    -0.07
    POSITIVE LOGITS
    办法
    0.08
     Walker
    0.08
    时候
    0.08
     knack
    0.07
    나라
    0.07
    -way
    0.07
    ални
    0.07
     Vent
    0.07
     embodiment
    0.07
    냐
    0.07
    Activations Density 0.079%

    No Known Activations