© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47643
    Prev
    Next
    INDEX
    Explanations

    Y

    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
     mentre
    -0.08
     professionnel
    -0.08
     gebracht
    -0.08
    annin
    -0.08
     tine
    -0.07
     হাঁ
    -0.07
    ুভ
    -0.07
    MIC
    -0.07
     yayin
    -0.07
    ’action
    -0.07
    POSITIVE LOGITS
    ığını
    0.10
    ืนยัน
    0.10
    ansı
    0.10
    ığın
    0.09
    ோ
    0.08
    ans
    0.08
    ön
    0.08
    önt
    0.08
    ற்ப
    0.08
     Osaka
    0.08
    Activations Density 0.001%

    No Known Activations