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. 77371
    Prev
    Next
    INDEX
    Explanations

    buildings and architecture

    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
     encounters
    -0.09
     declines
    -0.09
    .Dictionary
    -0.09
     persecut
    -0.08
    ”
    -0.08
     NSMutable
    -0.08
     medieval
    -0.08
     historically
    -0.08
    മാണ്
    -0.08
    .dictionary
    -0.08
    POSITIVE LOGITS
     sleek
    0.11
     renovation
    0.11
     الجديدة
    0.10
     renovated
    0.09
     newer
    0.09
     new
    0.09
     newest
    0.09
     కొత్త
    0.09
     stainless
    0.09
     сооруж
    0.08
    Activations Density 0.058%

    No Known Activations