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. 11-RESID-POST-AA
    6. 12021
    Prev
    Next
    INDEX
    Explanations

    a

    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
     Δ
    -0.08
     unified
    -0.08
     zd
    -0.08
    ,value
    -0.08
    avery
    -0.08
     Delta
    -0.08
    -0.08
     ə
    -0.08
     opoz
    -0.07
     value
    -0.07
    POSITIVE LOGITS
    آخر
    0.09
    访
    0.08
    _ping
    0.08
    _focus
    0.08
    .last
    0.08
    Ping
    0.08
     иди
    0.07
    কা
    0.07
    мас
    0.07
     Till
    0.07
    Activations Density 0.000%

    No Known Activations