© 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. 64971
    Prev
    Next
    INDEX
    Explanations

    more

    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
     Rudolf
    -0.08
     Ding
    -0.08
    Evt
    -0.08
    gifter
    -0.07
    .sn
    -0.07
     eb
    -0.07
     afgelopen
    -0.07
    евич
    -0.07
     Win
    -0.07
     Southwest
    -0.07
    POSITIVE LOGITS
    versa
    0.08
    KEA
    0.07
    ਜ਼
    0.07
    ધી
    0.07
     آن
    0.07
     highway
    0.07
     samlet
    0.07
    rails
    0.07
     trate
    0.07
     बनाई
    0.07
    Activations Density 0.230%

    No Known Activations