© 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. 6488
    Prev
    Next
    INDEX
    Explanations

    غ

    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
    izas
    -0.09
    -do
    -0.09
    ixin
    -0.09
    onza
    -0.08
    do
    -0.08
    /do
    -0.08
    arked
    -0.08
    ixi
    -0.08
    ��
    -0.08
    çə
    -0.08
    POSITIVE LOGITS
    ਤੀ
    0.10
    ایت
    0.10
    үг
    0.09
    لی
    0.09
    ալի
    0.09
    урда
    0.09
    ائی
    0.09
    יגה
    0.09
    алт
    0.08
    الات
    0.08
    Activations Density 0.002%

    No Known Activations