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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 67945
    Prev
    Next
    INDEX
    Explanations

    based

    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
    -0.08
     दुर्घ
    -0.08
    相談
    -0.08
     interrupted
    -0.08
     Aero
    -0.08
     użytk
    -0.07
    .worker
    -0.07
     edible
    -0.07
     troubleshooting
    -0.07
     Dmit
    -0.07
    POSITIVE LOGITS
     penal
    0.10
     incentiv
    0.10
     Obamacare
    0.09
    .Score
    0.08
     penalty
    0.08
     wirtschaft
    0.08
     shr
    0.08
    HW
    0.08
     الذ
    0.08
     insurers
    0.08
    Activations Density 0.013%

    No Known Activations