© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 108700
    Prev
    Next
    INDEX
    Explanations

    the

    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
     problemer
    -0.08
     følger
    -0.08
    Toute
    -0.08
    چار
    -0.08
    Tiet
    -0.08
     Spaß
    -0.08
    ";}↵
    -0.08
    動漫
    -0.08
     antics
    -0.08
     sexy
    -0.08
    POSITIVE LOGITS
     Eternal
    0.09
     decree
    0.09
     cust
    0.08
     परिषद
    0.08
     Providence
    0.08
     council
    0.08
     verlassen
    0.07
     Gaia
    0.07
     puh
    0.07
     covenant
    0.07
    Activations Density 0.072%

    No Known Activations