© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 79369
    Prev
    Next
    INDEX
    Explanations

    Interval intersections (maximums)

    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
     тысячи
    -0.08
     frantic
    -0.08
     Thousands
    -0.08
     beside
    -0.08
     thousands
    -0.08
     verteilt
    -0.08
    \Has
    -0.07
    <Transaction
    -0.07
    =False
    -0.07
    딩
    -0.07
    POSITIVE LOGITS
    max
    0.09
    midt
    0.09
    _max
    0.08
    meet
    0.08
    ункт
    0.08
    xaf
    0.08
    加盟
    0.08
     Treffen
    0.08
    athon
    0.07
     Coordin
    0.07
    Activations Density 0.009%

    No Known Activations