Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2324
    Prev
    Next
    INDEX
    Explanations

    *

    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
     illusions
    -0.07
    nav
    -0.07
     infinity
    -0.07
    learn
    -0.07
    control
    -0.07
     vas
    -0.07
     સુ
    -0.06
     continental
    -0.06
     referrals
    -0.06
     conducts
    -0.06
    POSITIVE LOGITS
    妇
    0.08
     Fy
    0.08
     nol
    0.08
    اتو
    0.08
    ,加
    0.08
    子的
    0.08
    ся
    0.08
    季
    0.08
     Cliff
    0.07
    絡
    0.07
    Activations Density 0.001%

    No Known Activations