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. 65757
    Prev
    Next
    INDEX
    Explanations

    array mapping and javascript

    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
     faction
    -0.08
     evade
    -0.08
    Buildings
    -0.08
     wav
    -0.08
     diverted
    -0.08
     electromagnetic
    -0.08
     deireadh
    -0.08
     gypsum
    -0.07
    akty
    -0.07
    .Dev
    -0.07
    POSITIVE LOGITS
    (predicate
    0.10
     Leib
    0.09
    函数
    0.09
    思想
    0.09
    _executor
    0.09
    .Invoke
    0.09
    哲
    0.09
    .Predicate
    0.09
     filosofia
    0.09
    Functor
    0.09
    Activations Density 0.009%

    No Known Activations