© 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. 3-RESID-POST-AA
    11. 12814
    Prev
    Next
    INDEX
    Explanations

    RNA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bish
    -0.09
     handbags
    -0.08
     электронной
    -0.08
     бис
    -0.08
     collectible
    -0.08
     erhält
    -0.08
    收藏
    -0.08
    获
    -0.08
    睛
    -0.07
     Auctions
    -0.07
    POSITIVE LOGITS
    饭
    0.08
    kot
    0.08
    飯
    0.08
     exped
    0.07
     sectional
    0.07
    sche
    0.07
     congest
    0.07
     kina
    0.07
     chassis
    0.07
    tile
    0.07
    Activations Density 0.010%

    No Known Activations