© 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. 68224
    Prev
    Next
    INDEX
    Explanations

    Circuit breakers and system design

    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
     EURO
    -0.09
     Euro
    -0.09
    Euro
    -0.08
     DV
    -0.08
     DSS
    -0.08
     DVD
    -0.08
    IANT
    -0.08
     Dill
    -0.07
     HOW
    -0.07
    htdocs
    -0.07
    POSITIVE LOGITS
     resil
    0.13
     resilience
    0.12
     resilient
    0.10
     debilit
    0.10
     mitig
    0.09
    Limiter
    0.09
     retries
    0.09
     Retry
    0.09
     retry
    0.09
    razi
    0.09
    Activations Density 0.001%

    No Known Activations