© 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. 3-RESID-POST-AA
    11. 1163
    Prev
    Next
    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    াদি
    -0.08
     നടത്തുന്ന
    -0.08
    positivo
    -0.07
    打一
    -0.07
     sorr
    -0.07
     estadual
    -0.07
     interno
    -0.07
     Mm
    -0.07
     prides
    -0.07
     segundos
    -0.07
    POSITIVE LOGITS
     ticker
    0.09
     pilgrimage
    0.08
    Coin
    0.08
     quota
    0.08
    Saga
    0.08
     turbo
    0.07
     ru
    0.07
     collision
    0.07
     saga
    0.07
    Jay
    0.07
    Activations Density 0.005%

    No Known Activations