Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12599
    Prev
    Next
    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     judges
    -0.08
     inex
    -0.07
     hopefully
    -0.07
    供
    -0.07
     knit
    -0.07
    เช
    -0.07
    خته
    -0.07
    ikot
    -0.07
     rosa
    -0.07
    搭
    -0.07
    POSITIVE LOGITS
     Lind
    0.08
     Olga
    0.08
     TPS
    0.08
     Thur
    0.07
     Gabe
    0.07
     Sidd
    0.07
     ਕਿ
    0.07
    eg
    0.07
    រ�
    0.07
     അവ
    0.07
    Activations Density 0.058%

    No Known Activations