© 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. 12731
    Prev
    Next
    INDEX
    Explanations

    翻

    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
     Anc
    -0.07
     청
    -0.07
     Pav
    -0.07
    lijn
    -0.07
     Tenn
    -0.07
     ripe
    -0.07
     oval
    -0.07
    ogn
    -0.07
     ph
    -0.07
     Ile
    -0.07
    POSITIVE LOGITS
     �
    0.07
    找
    0.07
     trag
    0.07
     elevations
    0.07
     elected
    0.07
    ESTAMP
    0.07
    ണ്ട്
    0.07
    SERVICE
    0.07
    াদি
    0.07
    EI
    0.07
    Activations Density 0.003%

    No Known Activations