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. 12706
    Prev
    Next
    INDEX
    Explanations

    blog introductions

    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
     scalable
    -0.08
     istem
    -0.07
    成人
    -0.07
    oba
    -0.07
     adults
    -0.07
     adulto
    -0.07
     intelligent
    -0.07
    ikipedia
    -0.07
     起
    -0.07
    {}\
    -0.07
    POSITIVE LOGITS
     이번
    0.11
     diesmal
    0.11
    今回は
    0.10
     এবার
    0.10
    이번
    0.10
     trochu
    0.09
    題
    0.09
    -packed
    0.09
    acağız
    0.09
     slightly
    0.08
    Activations Density 0.317%

    No Known Activations