© 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. 47111
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     சொ
    -0.09
     Mang
    -0.08
    loa
    -0.08
    goods
    -0.08
     тыс
    -0.07
    champ
    -0.07
    Про
    -0.07
    Venta
    -0.07
     Lone
    -0.07
    pegawai
    -0.07
    POSITIVE LOGITS
    ോറ
    0.08
    薦
    0.08
     AMG
    0.08
    ुक
    0.08
    प्र
    0.07
     crawling
    0.07
     dubb
    0.07
    日に
    0.07
    例えば
    0.07
    ُن
    0.07
    Activations Density 0.034%

    No Known Activations