© 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. 91307
    Prev
    Next
    INDEX
    Explanations

    with

    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
     nedeniyle
    -0.09
    irq
    -0.08
     판단
    -0.08
     종료
    -0.08
     여부
    -0.08
     iverm
    -0.08
    ycles
    -0.08
    ár
    -0.08
     Δ
    -0.08
    udsman
    -0.08
    POSITIVE LOGITS
     bustling
    0.10
     nightlife
    0.10
    音乐
    0.10
    城市
    0.09
     woman
    0.09
     antiques
    0.09
    都市
    0.09
     studio
    0.09
    餐
    0.09
    街
    0.09
    Activations Density 0.020%

    No Known Activations