© 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. 726
    Prev
    Next
    INDEX
    Explanations

    Hotspot/Popular

    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
     coexist
    -0.08
     wobei
    -0.08
    યોગ
    -0.07
    योग
    -0.07
    ->$
    -0.07
    XL
    -0.07
     interpersonal
    -0.07
    ->{$
    -0.07
    essor
    -0.07
    prov
    -0.07
    POSITIVE LOGITS
     반복
    0.09
    ndata
    0.09
     dati
    0.08
    热点
    0.08
     partagé
    0.08
     అంశ
    0.08
     چیز
    0.08
     데이터를
    0.08
     Teg
    0.08
    Demand
    0.07
    Activations Density 0.002%

    No Known Activations