© 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. 63636
    Prev
    Next
    INDEX
    Explanations

    mostly

    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
    30
    -0.08
    230
    -0.08
    23
    -0.08
    135
    -0.07
     inconvenient
    -0.07
    Do
    -0.07
    nef
    -0.07
     двад
    -0.07
     Do
    -0.07
     Monsieur
    -0.07
    POSITIVE LOGITS
     기반
    0.11
     આધાર
    0.11
     ఆధ
    0.10
     ভিত্ত
    0.10
     आधारित
    0.10
    Driven
    0.09
    -driven
    0.09
     ориент
    0.09
     Grundlage
    0.09
    elateerde
    0.09
    Activations Density 0.058%

    No Known Activations