© 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. 23-RESID-POST-AA
    11. 96664
    Prev
    Next
    INDEX
    Explanations

    say "pen"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ારીઓ
    -0.08
    ાર્�
    -0.08
    िंद
    -0.08
    ोर
    -0.08
    	auto
    -0.08
     auto
    -0.08
    arum
    -0.08
    auto
    -0.08
    ிக்கப்பட்ட
    -0.08
    reurs
    -0.07
    POSITIVE LOGITS
     brez
    0.08
     ಗಮನ
    0.08
     prefers
    0.08
     предпоч
    0.08
     préfère
    0.07
    vē
    0.07
     pou
    0.07
     prefer
    0.07
     Prefer
    0.07
     Pren
    0.07
    Activations Density 0.000%

    No Known Activations