© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1274
    Prev
    Next
    INDEX
    Explanations

    自动

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mus
    -0.09
    teni
    -0.08
    овая
    -0.08
     lived
    -0.08
    突
    -0.08
     haul
    -0.08
     vécu
    -0.07
    险
    -0.07
     indígenas
    -0.07
    _pix
    -0.07
    POSITIVE LOGITS
     自动
    0.11
     otomatis
    0.10
    /manual
    0.10
     түрде
    0.09
    自动
    0.09
    изирован
    0.09
     automatically
    0.09
     자동
    0.09
     автомат
    0.09
    .Aut
    0.08
    Activations Density 0.023%

    No Known Activations