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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 130967
    Prev
    Next
    INDEX
    Explanations

    Thucydides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .fre
    -0.09
    -0.08
    Fre
    -0.08
     shipments
    -0.08
    פ
    -0.08
     Fre
    -0.07
    cuts
    -0.07
    imates
    -0.07
     insurers
    -0.07
     obtain
    -0.07
    POSITIVE LOGITS
    (sound
    0.08
     ↵	↵
    0.08
     estab
    0.08
     Psycho
    0.08
     schiz
    0.08
    (background
    0.08
     Boden
    0.07
     Bach
    0.07
     poł
    0.07
    �
    0.07
    Activations Density 0.000%

    No Known Activations