© 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. 112330
    Prev
    Next
    INDEX
    Explanations

    image generation prompts

    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
    ريك
    -0.08
    -0.08
    FOUND
    -0.08
    registr
    -0.08
    esten
    -0.08
    ناول
    -0.08
    -même
    -0.08
    registered
    -0.07
    collapsed
    -0.07
    Rece
    -0.07
    POSITIVE LOGITS
     എന്നിവ
    0.11
     आदि
    0.10
     વગેરે
    0.09
     וכו
    0.08
     തുടങ്ങിയ
    0.08
    等等
    0.08
     എന്നീ
    0.08
     valamint
    0.08
     अउ
    0.08
     etc
    0.07
    Activations Density 0.041%
    No Known Activations