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. 131066
    Prev
    Next
    INDEX
    Explanations

    /res

    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
    goto
    -0.08
    jin
    -0.08
    init
    -0.08
    choose
    -0.08
    addition
    -0.08
    spl
    -0.08
    šen
    -0.08
    -0.08
    setup
    -0.08
    simpl
    -0.08
    POSITIVE LOGITS
    /android
    0.09
     android
    0.09
     haus
    0.08
     ios
    0.08
     Flutter
    0.08
    �
    0.08
    /mobile
    0.08
     "${
    0.07
    _android
    0.07
     Tradition
    0.07
    Activations Density 0.000%

    No Known Activations