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. 49293
    Prev
    Next
    INDEX
    Explanations

    achieve

    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
     Carter
    -0.08
     Vander
    -0.08
     Ré
    -0.08
    萨
    -0.08
     فکر
    -0.08
     Hass
    -0.08
     Sachs
    -0.07
    キャン
    -0.07
    ンサ
    -0.07
     Rah
    -0.07
    POSITIVE LOGITS
     lung
    0.08
     Lung
    0.07
     olu
    0.07
    ло
    0.07
     gew
    0.07
     tomando
    0.07
     Odd
    0.07
     urine
    0.07
    .Б
    0.07
     Protective
    0.07
    Activations Density 0.828%

    No Known Activations