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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68520
    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
     Monetary
    -0.08
    出票
    -0.08
     иш
    -0.08
     cumin
    -0.08
    第
    -0.08
     cafeter
    -0.08
     balc
    -0.08
    .bt
    -0.08
     brokers
    -0.07
     declares
    -0.07
    POSITIVE LOGITS
     abilities
    0.10
     способность
    0.10
     díky
    0.09
     способности
    0.09
     regener
    0.09
    能力
    0.09
     traits
    0.08
     Fähigkeit
    0.08
    Ability
    0.08
    Abilities
    0.08
    Activations Density 0.004%

    No Known Activations