© 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. 3-RESID-POST-AA
    11. 1168
    Prev
    Next
    INDEX
    Explanations

    первую

    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
     das
    -0.08
     atheist
    -0.07
    isasi
    -0.07
     diver
    -0.07
    Arab
    -0.07
    Div
    -0.07
    Disp
    -0.07
     pe
    -0.07
     diff
    -0.07
     ura
    -0.07
    POSITIVE LOGITS
    事故
    0.09
    有关
    0.08
     Vì
    0.08
    你好
    0.08
    赞
    0.07
    prest
    0.07
     quake
    0.07
    哭
    0.07
     Hou
    0.07
     Tach
    0.07
    Activations Density 0.000%

    No Known Activations