© 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. 79312
    Prev
    Next
    INDEX
    Explanations

    academic writing

    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
     comfy
    -0.11
     messed
    -0.11
     yummy
    -0.10
     guys
    -0.09
     Leute
    -0.09
     pretending
    -0.09
     folks
    -0.09
     gotta
    -0.09
     nicer
    -0.08
     guy
    -0.08
    POSITIVE LOGITS
     requisite
    0.11
     deline
    0.10
     pertinent
    0.10
    。然而
    0.09
     ostens
    0.09
     elucid
    0.09
     amalg
    0.09
     conglomer
    0.09
     disparate
    0.09
     unparalleled
    0.09
    Activations Density 0.182%

    No Known Activations