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. 30806
    Prev
    Next
    INDEX
    Explanations

    computer science

    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
     /^[
    -0.09
    international
    -0.08
    .bo
    -0.08
     plein
    -0.08
     internacional
    -0.08
     BLACK
    -0.08
     Böl
    -0.08
     Ví
    -0.08
     Bachelor
    -0.08
     Internationale
    -0.08
    POSITIVE LOGITS
     prat
    0.07
    过程中
    0.07
     equality
    0.07
    Convers
    0.07
     ainakin
    0.07
     convers
    0.07
    0.07
     pedal
    0.07
     adet
    0.07
     constructed
    0.07
    Activations Density 0.001%

    No Known Activations