© 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. 23-RESID-POST-AA
    11. 48028
    Prev
    Next
    INDEX
    Explanations

    物

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wɔn
    -0.09
    វ
    -0.08
     Ambul
    -0.08
     balcony
    -0.08
     சீ
    -0.08
    obao
    -0.08
     மூ
    -0.07
     Vendor
    -0.07
     Venezuel
    -0.07
     CN
    -0.07
    POSITIVE LOGITS
    語
    0.12
    语
    0.09
    결
    0.08
     stuk
    0.08
    形式
    0.08
    gesch
    0.08
    事
    0.08
     syntax
    0.08
    Laren
    0.08
     verhalen
    0.08
    Activations Density 0.001%

    No Known Activations