Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 61184
    Prev
    Next
    INDEX
    Explanations

    16

    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
    ore
    -0.07
     berupa
    -0.07
    arau
    -0.07
    atı
    -0.07
     ble
    -0.07
    馨
    -0.07
     exfol
    -0.07
    atua
    -0.07
    -0.06
     adjunct
    -0.06
    POSITIVE LOGITS
     svi
    0.10
     সাল
    0.08
     totalt
    0.08
    GIN
    0.08
     todas
    0.08
     সবাই
    0.08
    (circle
    0.07
     બધ
    0.07
    פּר
    0.07
    (pref
    0.07
    Activations Density 0.003%

    No Known Activations