© 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. 7-RESID-POST-AA
    11. 1173
    Prev
    Next
    INDEX
    Explanations

    slightly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Basics
    -0.09
     Singular
    -0.09
     Basilica
    -0.09
    uala
    -0.08
    iky
    -0.08
     reportedly
    -0.08
     fondament
    -0.08
     Structure
    -0.08
    -elles
    -0.08
    conditionally
    -0.08
    POSITIVE LOGITS
     prompts
    0.08
     kept
    0.08
     preset
    0.08
     váš
    0.07
     maintaining
    0.07
     cool
    0.07
    0.07
     delic
    0.07
     ilustr
    0.07
     ihtiyaç
    0.07
    Activations Density 0.000%
    No Known Activations