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. 15-RESID-POST-AA
    6. 71
    Prev
    Next
    INDEX
    Explanations

    say Javascript const/export

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,y
    -0.08
     irons
    -0.08
    Orbit
    -0.07
    ्यात
    -0.07
    og
    -0.07
    pflicht
    -0.07
    Lead
    -0.07
     Manning
    -0.07
    મે
    -0.07
    armen
    -0.07
    POSITIVE LOGITS
     shortcut
    0.09
     الموقع
    0.09
     shortcuts
    0.08
    .ff
    0.08
     shorthand
    0.08
     typed
    0.08
     usable
    0.08
     kollha
    0.08
     handige
    0.08
    atég
    0.08
    Activations Density 0.001%

    No Known Activations