© 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. 11-RESID-POST-AA
    11. 26580
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nghệ
    -0.08
     déplac
    -0.08
     hê
    -0.08
     investi
    -0.08
     dě
    -0.08
    ञ्ज
    -0.08
    stake
    -0.08
     shirk
    -0.08
     negosyo
    -0.08
     leed
    -0.08
    POSITIVE LOGITS
    ировать
    0.08
     Mark
    0.08
    çon
    0.07
    ирование
    0.07
    aphyl
    0.07
    Cnt
    0.07
    ">
    0.07
    Spin
    0.07
     preparing
    0.07
    pic
    0.07
    Activations Density 0.012%

    No Known Activations