© 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. 91438
    Prev
    Next
    INDEX
    Explanations

    z

    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
     streamed
    -0.08
     monk
    -0.07
     Messenger
    -0.07
     imbere
    -0.07
    enade
    -0.07
     ngen
    -0.07
     fresco
    -0.07
     Trung
    -0.07
    -0.07
     Umoja
    -0.07
    POSITIVE LOGITS
     digging
    0.08
    Thinking
    0.08
     überrasch
    0.07
     застав
    0.07
    Weekend
    0.07
    splice
    0.07
    中文版
    0.07
     sorpr
    0.07
     Überrasch
    0.07
    spar
    0.07
    Activations Density 0.000%
    No Known Activations