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. 23-RESID-POST-AA
    6. 98385
    Prev
    Next
    INDEX
    Explanations

    Realm, SQLite

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JMenu
    -0.09
    124
    -0.08
    	String
    -0.08
    	menu
    -0.08
     figure
    -0.08
     culturelle
    -0.08
    .mouse
    -0.08
    عام
    -0.08
     forty
    -0.08
     figura
    -0.08
    POSITIVE LOGITS
     Realm
    0.23
     Room
    0.20
    Realm
    0.18
     SQLite
    0.17
    Room
    0.17
     realm
    0.16
     ROOM
    0.15
    .realm
    0.15
    .Room
    0.15
    .room
    0.15
    Activations Density 0.005%

    No Known Activations