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. 43825
    Prev
    Next
    INDEX
    Explanations

    and

    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
    'oe
    -0.09
    /km
    -0.09
    ’œuvre
    -0.08
     someday
    -0.08
    avigate
    -0.08
     white
    -0.07
    /cloud
    -0.07
    _NOT
    -0.07
    /fonts
    -0.07
    /xhtml
    -0.07
    POSITIVE LOGITS
    bibigay
    0.09
    ความ
    0.08
    ydney
    0.08
     delegated
    0.08
     distract
    0.08
     번째
    0.08
     adicional
    0.08
     נוספים
    0.08
     deleg
    0.08
    την
    0.08
    Activations Density 0.008%

    No Known Activations