© 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. 112678
    Prev
    Next
    INDEX
    Explanations

    supercalifragilisticexpialidocious and honeycomb

    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
     fragments
    -0.08
     installments
    -0.08
     panties
    -0.08
     pockets
    -0.08
     LLC
    -0.08
    ρθ
    -0.08
     RMB
    -0.08
     bà
    -0.08
     infr
    -0.08
    女
    -0.07
    POSITIVE LOGITS
     aantal
    0.08
    นั้น
    0.08
    irdi
    0.08
    _SECTION
    0.08
    Military
    0.08
    meter
    0.07
    læ
    0.07
     revered
    0.07
    orn
    0.07
     Apocalypse
    0.07
    Activations Density 0.015%

    No Known Activations