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. 12683
    Prev
    Next
    INDEX
    Explanations

    seat

    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
     MO
    -0.08
    缩
    -0.07
     piles
    -0.07
    MO
    -0.07
    Mocks
    -0.07
     dalam
    -0.07
    ASC
    -0.07
     अफ
    -0.07
     stripped
    -0.07
     boiling
    -0.07
    POSITIVE LOGITS
    ाकृतिक
    0.09
    sending
    0.09
    ционного
    0.08
     Obtener
    0.08
    әһ
    0.08
    ifers
    0.08
     öğren
    0.08
     réservation
    0.08
     Sending
    0.08
    циям
    0.08
    Activations Density 0.004%

    No Known Activations