© 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. 19-RESID-POST-AA
    11. 103435
    Prev
    Next
    INDEX
    Explanations

    code

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    عتبر
    -0.09
     مڪمل
    -0.08
     رع
    -0.08
     соблюдать
    -0.07
    vival
    -0.07
    icial
    -0.07
    -0.07
    eno
    -0.07
     દરમિયાન
    -0.07
    فاوت
    -0.07
    POSITIVE LOGITS
     pointing
    0.26
     directing
    0.25
     directs
    0.23
     linking
    0.22
     direcion
    0.21
     redirect
    0.21
     menuju
    0.20
     aponta
    0.20
     connects
    0.20
     apont
    0.20
    Activations Density 0.153%
    No Known Activations