© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68243
    Prev
    Next
    INDEX
    Explanations

    reuse

    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
     worse
    -0.08
     overt
    -0.07
    .imshow
    -0.07
    800
    -0.07
    _next
    -0.07
     bip
    -0.07
     therapy
    -0.07
     barely
    -0.07
     provoc
    -0.07
    oscow
    -0.07
    POSITIVE LOGITS
     reusable
    0.23
    Reusable
    0.19
     reused
    0.19
     reutil
    0.19
     reuse
    0.16
    Reuse
    0.15
    重复
    0.12
    共享
    0.12
    reuse
    0.12
     recurring
    0.12
    Activations Density 0.017%

    No Known Activations