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

    Neuronpedia

    Jacobian LensNEW
    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. 113520
    Prev
    Next
    INDEX
    Explanations

    Daubechies wavelets

    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
     multinational
    -0.08
     mutated
    -0.08
     united
    -0.08
     aufnehmen
    -0.07
     Kingdom
    -0.07
     approval
    -0.07
    批准
    -0.07
     fluctu
    -0.07
    览
    -0.07
    -0.07
    POSITIVE LOGITS
     atilẹ
    0.09
    Stopping
    0.08
     igbesi
    0.08
    چر
    0.08
     ṣiṣẹ
    0.08
    بية
    0.08
     diseñada
    0.08
     проститутки
    0.08
     personalmente
    0.08
     abiertos
    0.08
    Activations Density 0.001%
    No Known Activations