© 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. 23-RESID-POST-AA
    11. 6069
    Prev
    Next
    INDEX
    Explanations

    center

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    central
    -0.10
     केंद्रीय
    -0.09
     কেন্দ
    -0.09
     central
    -0.09
     centralized
    -0.09
    。同
    -0.08
    .")↵
    -0.08
     केंद
    -0.08
    。当然
    -0.08
     Etc
    -0.08
    POSITIVE LOGITS
     ensuring
    0.12
     creating
    0.11
     allowing
    0.11
     laissant
    0.11
     რათა
    0.11
     letting
    0.11
     showcasing
    0.11
     بحيث
    0.10
     dejando
    0.10
     showing
    0.10
    Activations Density 0.017%

    No Known Activations