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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 106119
    Prev
    Next
    INDEX
    Explanations

    legal acts

    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
    tein
    -0.07
     Tram
    -0.07
    Photos
    -0.07
     نور
    -0.07
     horribly
    -0.07
    ever
    -0.07
     stimmt
    -0.07
     photos
    -0.07
     chemo
    -0.07
     chefs
    -0.07
    POSITIVE LOGITS
    (addr
    0.08
     enacted
    0.08
     আও
    0.08
    (adj
    0.08
    以下简称
    0.08
    টির
    0.07
    (address
    0.07
    ଗ
    0.07
     বাজ
    0.07
     spanking
    0.07
    Activations Density 0.009%

    No Known Activations