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. 114127
    Prev
    Next
    INDEX
    Explanations

    Number representations

    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
     чек
    -0.09
     оцен
    -0.08
     đánh
    -0.08
    ครับ
    -0.08
    /she
    -0.08
    .beans
    -0.08
     ചെയ്തത്
    -0.08
     Fest
    -0.08
     руках
    -0.08
     เพื่อ
    -0.07
    POSITIVE LOGITS
     panjang
    0.08
     ví
    0.08
     Gy
    0.08
     centrifugal
    0.07
     encontrarás
    0.07
    irr
    0.07
     spot
    0.07
    472
    0.07
    中特
    0.07
     प्रव
    0.07
    Activations Density 0.006%

    No Known Activations