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. 43016
    Prev
    Next
    INDEX
    Explanations

    :

    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
    .imgur
    -0.09
    ぜひ
    -0.08
     Теперь
    -0.08
     fett
    -0.08
    jek
    -0.08
    AVAILABLE
    -0.08
    上映
    -0.08
    есь
    -0.07
     entstand
    -0.07
     ему
    -0.07
    POSITIVE LOGITS
    Generally
    0.09
     Basics
    0.09
    Basics
    0.09
     typically
    0.09
     둘
    0.09
     fundamentally
    0.09
     generally
    0.08
     basics
    0.08
    人在
    0.08
    通常
    0.08
    Activations Density 0.103%

    No Known Activations