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. 58318
    Prev
    Next
    INDEX
    Explanations

    gold carat values

    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
     seg
    -0.07
    ראות
    -0.07
     Early
    -0.07
     *
    ↵
    -0.07
    ~~~~
    -0.07
    snap
    -0.07
    se
    -0.07
     fò
    -0.07
     Concert
    -0.07
    .Repositories
    -0.07
    POSITIVE LOGITS
    款
    0.09
    -tone
    0.08
     krás
    0.08
     fiber
    0.08
     kand
    0.08
     lust
    0.08
     kolor
    0.08
     warna
    0.08
     kadar
    0.08
    以内
    0.08
    Activations Density 0.005%

    No Known Activations