Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 59514
    Prev
    Next
    INDEX
    Explanations

    durations with days

    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
     Trinidad
    -0.09
     televisión
    -0.08
     spilled
    -0.08
    ‍ണ
    -0.08
     ligera
    -0.08
     propulsion
    -0.08
    ungal
    -0.08
     Arb
    -0.08
    ണ
    -0.08
     Garland
    -0.08
    POSITIVE LOGITS
    JWT
    0.08
     langleb
    0.08
     JWT
    0.08
    0.08
    _ONE
    0.07
    -week
    0.07
    _UPLOAD
    0.07
     CRUD
    0.07
    .JWT
    0.07
     session
    0.07
    Activations Density 0.001%

    No Known Activations