© 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. 91321
    Prev
    Next
    INDEX
    Explanations

    for

    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
     inoltre
    -0.08
    282
    -0.08
     له
    -0.07
     isə
    -0.07
     Marc
    -0.07
    ाँच
    -0.07
    *y
    -0.07
     mar
    -0.07
    :y
    -0.07
     Essence
    -0.07
    POSITIVE LOGITS
     וגם
    0.10
     respective
    0.08
    25
    0.07
    Tan
    0.07
     benefited
    0.07
    ijs
    0.07
    entrant
    0.07
     prensa
    0.07
     diesmal
    0.07
     beneficia
    0.07
    Activations Density 0.376%

    No Known Activations