© 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. 48024
    Prev
    Next
    INDEX
    Explanations

    造

    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
     вок
    -0.08
     preserv
    -0.07
     vaj
    -0.07
    izzes
    -0.07
     pall
    -0.07
     Üniversitesi
    -0.07
     paint
    -0.07
    lük
    -0.07
     Succ
    -0.07
     polis
    -0.07
    POSITIVE LOGITS
     అవకాశ
    0.08
     readings
    0.08
     Ci
    0.08
    Fk
    0.08
    possible
    0.08
     dung
    0.07
     દર
    0.07
     FU
    0.07
     الحال
    0.07
     luminous
    0.07
    Activations Density 0.003%

    No Known Activations