© 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. 54706
    Prev
    Next
    INDEX
    Explanations

    Returning to the beginning

    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
     حک
    -0.08
     Fenster
    -0.07
     Khr
    -0.07
     asio
    -0.07
     compreensão
    -0.07
     axios
    -0.07
     servidor
    -0.07
     Aos
    -0.07
     optimism
    -0.07
     hourly
    -0.07
    POSITIVE LOGITS
    kite
    0.09
    ort
    0.08
    itang
    0.08
    _:*
    0.08
     ҡатын
    0.08
     unheard
    0.08
     ముగ
    0.07
    Closing
    0.07
    _circle
    0.07
    mainder
    0.07
    Activations Density 0.006%

    No Known Activations