© 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. 45447
    Prev
    Next
    INDEX
    Explanations

    fail

    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
    തമ
    -0.08
     Pixar
    -0.08
     environmentally
    -0.08
    ၁
    -0.08
    ေး
    -0.08
     kilomet
    -0.08
     IFC
    -0.08
     оке
    -0.08
     meio
    -0.08
    环保
    -0.07
    POSITIVE LOGITS
     પ્રયાસ
    0.11
    Attempts
    0.11
     attempts
    0.11
    _attempt
    0.10
    attempt
    0.10
     verdachte
    0.10
    Attempt
    0.10
     попыт
    0.10
    攻击
    0.10
     ప్రయత్న
    0.09
    Activations Density 0.006%

    No Known Activations