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. 112961
    Prev
    Next
    INDEX
    Explanations

    do

    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
    icale
    -0.09
    IMAL
    -0.08
    _DISABLE
    -0.08
    ILO
    -0.08
    glig
    -0.08
     tarafından
    -0.08
    orl
    -0.08
    _nullable
    -0.08
    ILLI
    -0.08
    AVI
    -0.08
    POSITIVE LOGITS
     být
    0.08
     divertida
    0.08
    )!
    0.08
     Zustimmung
    0.08
    >#
    0.07
    .component
    0.07
     mood
    0.07
    🔥
    0.07
     sint
    0.07
     Beijing
    0.07
    Activations Density 0.013%

    No Known Activations