© 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. 129307
    Prev
    Next
    INDEX
    Explanations

    ographic

    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
    vei
    -0.08
    共产党
    -0.08
     Plates
    -0.08
    Recovered
    -0.08
    ksiä
    -0.08
    September
    -0.08
     Sever
    -0.08
     aps
    -0.07
     Anlagen
    -0.07
    seer
    -0.07
    POSITIVE LOGITS
     unrealistic
    0.08
     ningún
    0.08
     Eu
    0.08
     {
    0.07
     blue
    0.07
     надо
    0.07
     �
    0.07
    Eu
    0.07
     zor
    0.07
     jaz
    0.07
    Activations Density 0.003%

    No Known Activations