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. 102857
    Prev
    Next
    INDEX
    Explanations

    relative

    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
    akin
    -0.09
     Conn
    -0.08
     Salam
    -0.08
    kannt
    -0.08
     Machado
    -0.08
     Dres
    -0.07
     Carrera
    -0.07
    ules
    -0.07
     CSA
    -0.07
     Supporting
    -0.07
    POSITIVE LOGITS
    721
    0.08
    atest
    0.08
     positioning
    0.07
    而言
    0.07
     premieres
    0.07
     בין
    0.07
    این
    0.07
     sizing
    0.07
    .Priority
    0.07
    づ
    0.07
    Activations Density 0.009%

    No Known Activations