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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 113977
    Prev
    Next
    INDEX
    Explanations

    prototype

    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
     характериз
    -0.09
     vigilance
    -0.09
     Garantie
    -0.08
    科学院
    -0.08
     Segurança
    -0.08
     Tate
    -0.08
     Vlad
    -0.08
    涛
    -0.08
     Orte
    -0.08
     Pedra
    -0.08
    POSITIVE LOGITS
    制作
    0.11
     prototypes
    0.10
     제작
    0.10
     prototype
    0.09
    製
    0.08
     создания
    0.08
     sketches
    0.08
    Prototype
    0.08
    紙
    0.08
    /test
    0.07
    Activations Density 0.005%

    No Known Activations