Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53950
    Prev
    Next
    INDEX
    Explanations

    code files

    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
    魅
    -0.09
    推出
    -0.09
    criterion
    -0.08
    Bon
    -0.08
     шығ
    -0.08
    CARE
    -0.08
    phony
    -0.08
     caratteristiche
    -0.08
    威
    -0.08
    抢
    -0.08
    POSITIVE LOGITS
     Temporary
    0.09
     기록
    0.09
     sementara
    0.09
     ذخ
    0.09
     저장
    0.08
     Tempor
    0.08
     intermediary
    0.08
     transient
    0.08
     documenting
    0.08
     смесь
    0.08
    Activations Density 0.000%

    No Known Activations