© 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. 54829
    Prev
    Next
    INDEX
    Explanations

    survival

    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
    Eff
    -0.08
    োলা
    -0.07
    코
    -0.07
    -0.07
    flamm
    -0.07
    -0.07
    _sa
    -0.07
    Flags
    -0.07
     kreative
    -0.07
     executes
    -0.07
    POSITIVE LOGITS
     modest
    0.09
    patients
    0.09
     implanted
    0.09
     Narrow
    0.09
     cessation
    0.09
     فترة
    0.09
     implantation
    0.09
     пациент
    0.08
     ago
    0.08
     yuan
    0.08
    Activations Density 0.004%
    No Known Activations