© 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. 47287
    Prev
    Next
    INDEX
    Explanations

    Instructions

    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
     lucid
    -0.09
     Hym
    -0.08
    draft
    -0.08
    was
    -0.08
    juven
    -0.08
     Tennessee
    -0.07
    Religion
    -0.07
     schn
    -0.07
    avanaugh
    -0.07
     Jov
    -0.07
    POSITIVE LOGITS
    ÍT
    0.08
     Эта
    0.08
     silla
    0.07
    ：首页
    0.07
    metry
    0.07
    ítani
    0.06
     añad
    0.06
    的位置
    0.06
     ish
    0.06
    ksyon
    0.06
    Activations Density 0.000%

    No Known Activations