© 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. 47301
    Prev
    Next
    INDEX
    Explanations

    motherboard CPU sockets

    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
    -gener
    -0.08
    Tpl
    -0.08
     Dieu
    -0.08
    mages
    -0.08
    ünü
    -0.08
    Oxford
    -0.08
     Türki
    -0.07
    ━
    -0.07
     أننا
    -0.07
     GOD
    -0.07
    POSITIVE LOGITS
     recl
    0.08
     senha
    0.07
     требования
    0.07
     phon
    0.07
    7
    0.07
     lowered
    0.07
     פת
    0.07
    0.07
     vacancy
    0.07
     requisitos
    0.07
    Activations Density 0.003%
    No Known Activations