© 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. 1491
    Prev
    Next
    INDEX
    Explanations

    ots

    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
    烈
    -0.08
    惊
    -0.08
     surpass
    -0.08
    こと
    -0.08
    に
    -0.07
    �
    -0.07
    イ
    -0.07
    可靠
    -0.07
     défense
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     парамет
    0.08
     интерьер
    0.08
     машин
    0.08
     Lan
    0.08
    CLS
    0.07
     표시
    0.07
    bliche
    0.07
     bleaching
    0.07
     Machine
    0.07
     Nih
    0.07
    Activations Density 0.000%

    No Known Activations