© 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. 12756
    Prev
    Next
    INDEX
    Explanations

    AP

    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
    注文
    -0.08
     ber
    -0.08
    詳
    -0.07
    ละคร
    -0.07
     Emil
    -0.07
     удоб
    -0.07
     kin
    -0.07
    -av
    -0.07
    套
    -0.07
     kropp
    -0.07
    POSITIVE LOGITS
    景
    0.09
    天空
    0.09
     scenery
    0.08
     tuyệt
    0.08
     منظر
    0.08
     skies
    0.08
     magnifiques
    0.08
     풍
    0.08
     foliage
    0.08
     видом
    0.08
    Activations Density 0.064%

    No Known Activations