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. 11-RESID-POST-AA
    6. 78140
    Prev
    Next
    INDEX
    Explanations

    Kubernetes

    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
    Fun
    -0.09
     Ị
    -0.08
     joyful
    -0.08
     tł
    -0.08
     joyous
    -0.08
    насць
    -0.08
    句话
    -0.08
    ヤ
    -0.08
     yil
    -0.08
    ِن
    -0.08
    POSITIVE LOGITS
     preventing
    0.09
     prohib
    0.09
     inhib
    0.07
     verhindern
    0.07
     excepcional
    0.07
     inhibitor
    0.07
     elimin
    0.07
     empêcher
    0.07
     forb
    0.07
     excepc
    0.07
    Activations Density 0.000%

    No Known Activations