© 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. 45529
    Prev
    Next
    INDEX
    Explanations

    limits/potential

    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
    Gig
    -0.08
     usp
    -0.08
     inspire
    -0.08
     lect
    -0.08
     CSR
    -0.08
     comité
    -0.08
     spp
    -0.08
     кафед
    -0.08
     wak
    -0.08
    lectic
    -0.08
    POSITIVE LOGITS
     payouts
    0.11
     liquidation
    0.11
    本金
    0.11
     winnings
    0.10
     volatility
    0.10
     במקרה
    0.10
     amplification
    0.10
     risks
    0.10
    收益
    0.10
     pertes
    0.09
    Activations Density 0.008%

    No Known Activations