© 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. 78485
    Prev
    Next
    INDEX
    Explanations

    food provisions

    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
     spectral
    -0.08
    negative
    -0.08
     Spect
    -0.08
    Spect
    -0.08
     shadow
    -0.08
     negative
    -0.08
     Shadow
    -0.08
     negativo
    -0.07
     негатив
    -0.07
    Shadow
    -0.07
    POSITIVE LOGITS
     Ressourcen
    0.12
     ресурс
    0.12
     resources
    0.12
     ressources
    0.11
     consumed
    0.11
    .resources
    0.11
     consum
    0.11
    资源
    0.11
     Resources
    0.10
    Consum
    0.10
    Activations Density 0.051%

    No Known Activations