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. 111857
    Prev
    Next
    INDEX
    Explanations

    enzymes

    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
     persönliche
    -0.08
     speculative
    -0.08
     disruptive
    -0.08
    יפ
    -0.08
     kompet
    -0.08
     regulators
    -0.08
     seized
    -0.08
     interpersonal
    -0.07
    RIS
    -0.07
     mandated
    -0.07
    POSITIVE LOGITS
    enticator
    0.08
     cumul
    0.08
    Authenticator
    0.08
     cumulative
    0.07
    (App
    0.07
    Reporter
    0.07
     Katze
    0.07
    Error
    0.07
    Synchronization
    0.07
    <Menu
    0.07
    Activations Density 0.001%

    No Known Activations