© 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. 54937
    Prev
    Next
    INDEX
    Explanations

    guarantee

    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
     вариан
    -0.09
     roughly
    -0.08
     dimainkan
    -0.08
    Основ
    -0.08
     정도
    -0.08
    submenu
    -0.08
    主要
    -0.08
     примерно
    -0.08
     diperlukan
    -0.08
    Fis
    -0.08
    POSITIVE LOGITS
     Guarantee
    0.13
     guarantee
    0.12
     Guaranteed
    0.11
     garantit
    0.11
     Guarante
    0.11
     garant
    0.11
     gwar
    0.11
     garantiert
    0.11
     patented
    0.11
    Guarante
    0.11
    Activations Density 0.174%

    No Known Activations