© 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. 15-RESID-POST-AA
    11. 16250
    Prev
    Next
    INDEX
    Explanations

    ##

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ')'
    -0.09
     عدة
    -0.09
     obwohl
    -0.08
    enery
    -0.08
     depending
    -0.08
     izinto
    -0.08
     kostet
    -0.08
     فعل
    -0.08
    Depending
    -0.08
     likes
    -0.08
    POSITIVE LOGITS
     Designing
    0.10
     redesigned
    0.09
     Ambassador
    0.09
    ‐
    0.09
     revamped
    0.09
     designing
    0.09
     titled
    0.09
    打造
    0.09
     Blueprint
    0.08
    Blueprint
    0.08
    Activations Density 0.028%

    No Known Activations