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. 49291
    Prev
    Next
    INDEX
    Explanations

    digits

    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
     Rubber
    -0.08
     આત
    -0.08
     }))
    -0.08
     כול
    -0.08
     आत्म
    -0.08
    encers
    -0.08
    ’ai
    -0.08
    ume
    -0.07
    AIN
    -0.07
     Iedereen
    -0.07
    POSITIVE LOGITS
     spectacular
    0.08
     dando
    0.08
     espet
    0.08
    toc
    0.08
     complicado
    0.08
     giving
    0.08
    Build
    0.07
     handing
    0.07
     dusty
    0.07
    ကျ
    0.07
    Activations Density 0.055%

    No Known Activations