© 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. 48064
    Prev
    Next
    INDEX
    Explanations

    Contract/crypto Addresses

    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
     |_|
    -0.08
    osexual
    -0.08
    圈
    -0.08
    ンズ
    -0.07
     transformed
    -0.07
    hafte
    -0.07
     वटा
    -0.07
    固定
    -0.07
     পাৰে
    -0.07
    uelta
    -0.07
    POSITIVE LOGITS
     conco
    0.08
     lengthy
    0.08
     genealog
    0.08
     chal
    0.07
     opportun
    0.07
    0.07
    ઇ
    0.07
    เ�
    0.07
     Hans
    0.07
     Georg
    0.07
    Activations Density 0.006%
    No Known Activations