© 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. 50
    Prev
    Next
    INDEX
    Explanations

    Say

    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
    大的
    -0.07
    atto
    -0.07
    �
    -0.07
    vedo
    -0.07
     visar
    -0.07
     зеркало
    -0.07
    itchen
    -0.07
    emain
    -0.07
    aitre
    -0.07
    য়ন
    -0.07
    POSITIVE LOGITS
     matrícula
    0.08
    дерді
    0.08
    իբ
    0.08
    betr
    0.08
     پیشن
    0.08
    ಿಬ
    0.08
     آسی
    0.08
     alfabet
    0.08
     enige
    0.08
    ště
    0.07
    Activations Density 0.000%

    No Known Activations