© 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. 23-RESID-POST-AA
    11. 5789
    Prev
    Next
    INDEX
    Explanations

    т

    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
     giảm
    -0.08
     posed
    -0.08
     kise
    -0.07
     감소
    -0.07
    ERICA
    -0.07
     upang
    -0.07
     کاهش
    -0.07
     将
    -0.07
     toes
    -0.07
     kugira
    -0.07
    POSITIVE LOGITS
    верж
    0.18
    верд
    0.17
    verd
    0.10
    ვალი
    0.10
    ანხმ
    0.09
    вр
    0.09
    ือน
    0.09
    вер
    0.09
    immungen
    0.08
    ქვამ
    0.08
    Activations Density 0.001%

    No Known Activations