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. 9164
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ERRQ
    -0.09
     hạn
    -0.09
    ebox
    -0.09
     zapew
    -0.08
    rones
    -0.08
     tiên
    -0.08
    ải
    -0.08
     figured
    -0.08
     vấn
    -0.08
     billboard
    -0.08
    POSITIVE LOGITS
     fascinating
    0.08
     bacterial
    0.08
    Pause
    0.08
     gastric
    0.08
     Castilla
    0.07
    During
    0.07
     icyo
    0.07
    Deleting
    0.07
     attenuation
    0.07
     magní
    0.07
    Activations Density 0.002%

    No Known Activations