© 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. 95268
    Prev
    Next
    INDEX
    Explanations

    Nucleosynthesis and elements

    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
    -अ
    -0.08
    innen
    -0.08
    สู
    -0.08
     उदाहरण
    -0.07
     утра
    -0.07
    ील
    -0.07
     excelencia
    -0.07
     internos
    -0.07
    :innen
    -0.07
    ijl
    -0.07
    POSITIVE LOGITS
    ITY
    0.08
     padx
    0.07
     kín
    0.07
    ASY
    0.07
    Mk
    0.07
    _PAGE
    0.07
     Haag
    0.07
    marshaller
    0.07
     ami
    0.07
    MOD
    0.07
    Activations Density 0.000%

    No Known Activations