© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25229
    Prev
    Next
    INDEX
    Explanations

    code

    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
     estaremos
    -0.09
     Hurricane
    -0.08
     ciment
    -0.08
    840
    -0.08
    共产
    -0.08
    炎
    -0.08
    linge
    -0.08
     versche
    -0.07
    ိတ်
    -0.07
    akata
    -0.07
    POSITIVE LOGITS
     диапаз
    0.09
     grabbing
    0.09
     ranges
    0.08
     Pets
    0.08
    _RANGE
    0.08
     pym
    0.08
     range
    0.08
     rectangular
    0.07
     मैदान
    0.07
    .Matrix
    0.07
    Activations Density 0.004%

    No Known Activations