© 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. 11-RESID-POST-AA
    11. 64489
    Prev
    Next
    INDEX
    Explanations

    code

    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
     parlament
    -0.08
     Mata
    -0.08
     mata
    -0.08
    ipl
    -0.08
     gene
    -0.07
     Coursework
    -0.07
     jude
    -0.07
     xmm
    -0.07
     espada
    -0.07
     Gle
    -0.07
    POSITIVE LOGITS
     nuggets
    0.09
     DHCP
    0.08
    洞
    0.08
     toll
    0.08
     hunter
    0.08
     bri
    0.08
    -tooltip
    0.08
     مشتری
    0.07
    療
    0.07
    营销
    0.07
    Activations Density 0.039%

    No Known Activations