© 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. 29265
    Prev
    Next
    INDEX
    Explanations

    of

    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
    -0.09
     swirling
    -0.09
     echt
    -0.08
     �
    -0.07
     motto
    -0.07
     brood
    -0.07
     আশ
    -0.07
     fleeting
    -0.07
     במש
    -0.07
     alene
    -0.07
    POSITIVE LOGITS
     finalizar
    0.12
     پایان
    0.12
     termination
    0.11
    終了
    0.11
    解除
    0.11
     lõpet
    0.11
     শেষে
    0.10
    Finalize
    0.10
     culmination
    0.10
     конце
    0.10
    Activations Density 0.055%
    No Known Activations