© 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. 108600
    Prev
    Next
    INDEX
    Explanations

    ok

    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
     trẻ
    -0.08
     bj
    -0.07
     lưu
    -0.07
     shovel
    -0.07
     GMT
    -0.07
     perten
    -0.07
     obec
    -0.07
     glamorous
    -0.07
     hoạt
    -0.07
     serde
    -0.07
    POSITIVE LOGITS
     famously
    0.11
    Dup
    0.09
    _fault
    0.08
     Dup
    0.08
     ア
    0.08
    gum
    0.08
     Tand
    0.08
     Fault
    0.08
     dare
    0.08
     Mish
    0.08
    Activations Density 0.040%

    No Known Activations