© 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. 7-RESID-POST-AA
    11. 1449
    Prev
    Next
    INDEX
    Explanations

    Net

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ഞ്ച
    -0.08
     makin
    -0.08
     rele
    -0.08
    ંજ
    -0.07
     properly
    -0.07
     HIST
    -0.07
    ராக
    -0.07
    दिल
    -0.07
    arch
    -0.07
    .Detail
    -0.07
    POSITIVE LOGITS
    票
    0.08
    体系
    0.08
     Eto
    0.08
     espécie
    0.08
    整理
    0.08
     og
    0.07
    最新
    0.07
    兵
    0.07
    用途
    0.07
     Barre
    0.07
    Activations Density 0.000%

    No Known Activations