© 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. 2609
    Prev
    Next
    INDEX
    Explanations

    Timeout

    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
    wier
    -0.07
    �
    -0.07
     Cen
    -0.07
    امل
    -0.07
    olang
    -0.07
     recount
    -0.07
    ಪ್ರ
    -0.07
    featured
    -0.07
    ಆ
    -0.07
     आता
    -0.07
    POSITIVE LOGITS
     khỏi
    0.08
    Ath
    0.08
    0.07
     Williams
    0.07
     kiz
    0.07
     spirits
    0.07
     ..
    0.07
    ..
    0.07
     pann
    0.07
     Spirits
    0.07
    Activations Density 0.039%
    No Known Activations