© 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. 3-RESID-POST-AA
    11. 1460
    Prev
    Next
    INDEX
    Explanations

    Clearance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     совет
    -0.09
     Fir
    -0.08
     recomiendo
    -0.08
    Sar
    -0.08
     refres
    -0.08
     seda
    -0.08
     toastr
    -0.07
    еша
    -0.07
     בדי
    -0.07
     connex
    -0.07
    POSITIVE LOGITS
     食
    0.09
    食品
    0.08
    _lang
    0.08
    _detect
    0.07
     wpły
    0.07
    _argument
    0.07
    .restaurant
    0.07
     ken
    0.07
    _records
    0.07
    _LANG
    0.07
    Activations Density 0.000%

    No Known Activations