© 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. 3-RESID-POST-AA
    11. 2641
    Prev
    Next
    INDEX
    Explanations

    pod

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bif
    -0.09
    Spl
    -0.09
     woody
    -0.08
    たり
    -0.08
     bas
    -0.07
     السما
    -0.07
     bure
    -0.07
    ي
    -0.07
    sempel
    -0.07
     embodied
    -0.07
    POSITIVE LOGITS
     Clement
    0.08
     Diagram
    0.08
     sty
    0.08
     Challenger
    0.08
     wheel
    0.07
     paul
    0.07
     kosher
    0.07
     Ibiza
    0.07
    -wheel
    0.07
     Drawer
    0.07
    Activations Density 0.002%

    No Known Activations