© 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. 95353
    Prev
    Next
    INDEX
    Explanations

    ‑

    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
    ေရး
    -0.08
     probar
    -0.07
     switches
    -0.07
    |)↵
    -0.07
    _SWITCH
    -0.07
     excepcional
    -0.07
    61
    -0.07
    onek
    -0.07
     cen
    -0.07
    unidad
    -0.07
    POSITIVE LOGITS
     나는
    0.08
     女
    0.08
    她
    0.08
     辽
    0.08
     그녀
    0.07
    Pier
    0.07
     여자
    0.07
     leather
    0.07
     Tav
    0.07
    -as
    0.07
    Activations Density 0.028%

    No Known Activations