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. 45042
    Prev
    Next
    INDEX
    Explanations

    �

    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
     যুক্ত
    -0.08
     mente
    -0.07
    amar
    -0.07
    NEXT
    -0.07
    'll
    -0.07
     застав
    -0.07
    nc
    -0.07
    ssystem
    -0.07
     suites
    -0.07
    최
    -0.07
    POSITIVE LOGITS
     جدًا
    0.09
     sparse
    0.08
    闲
    0.08
     pas
    0.08
     scarce
    0.08
     الوزن
    0.08
     scant
    0.08
    -minded
    0.08
    rodd
    0.07
     टिक
    0.07
    Activations Density 0.007%

    No Known Activations