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. 77291
    Prev
    Next
    INDEX
    Explanations

    decibel calculation

    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
    �n
    -0.08
    <↵
    -0.07
    avel
    -0.07
     sixth
    -0.07
     น
    -0.07
     spiral
    -0.07
    iging
    -0.07
     Singapore
    -0.07
    台湾
    -0.07
    izzling
    -0.07
    POSITIVE LOGITS
     complains
    0.10
     republican
    0.09
     complaining
    0.09
    쓰기
    0.08
     rechaz
    0.08
    δικ
    0.08
     rejects
    0.08
     പരാത
    0.08
     நீத
    0.08
     oblast
    0.08
    Activations Density 0.001%

    No Known Activations