© 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. 64333
    Prev
    Next
    INDEX
    Explanations

    down

    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
     nationalism
    -0.07
     ত
    -0.07
    297
    -0.07
     पु
    -0.07
     protested
    -0.07
     וד
    -0.07
     সমস্ত
    -0.07
     দাবি
    -0.07
     সম্প্র
    -0.07
    _ph
    -0.07
    POSITIVE LOGITS
     écran
    0.11
     distractions
    0.09
    Distr
    0.09
     Distr
    0.09
    tais
    0.09
     electrónica
    0.09
     ηλικ
    0.08
     elektronische
    0.08
     बित
    0.08
     electrónicos
    0.08
    Activations Density 0.010%

    No Known Activations