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. 49027
    Prev
    Next
    INDEX
    Explanations

    regeneration

    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
    ective
    -0.08
    /v
    -0.07
    _CASE
    -0.07
    사의
    -0.07
     детал
    -0.07
    사가
    -0.07
    사를
    -0.07
     Tos
    -0.07
    यों
    -0.07
    وجه
    -0.07
    POSITIVE LOGITS
     replen
    0.17
     replenish
    0.16
     recharge
    0.15
     regeneration
    0.14
     obnov
    0.14
     heals
    0.14
     refill
    0.13
     regener
    0.13
     healing
    0.13
    恢复
    0.13
    Activations Density 0.010%

    No Known Activations