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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97058
    Prev
    Next
    INDEX
    Explanations

    blue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wechsel
    -0.09
    tabl
    -0.09
    pụtara
    -0.08
    chemist
    -0.08
    uteur
    -0.08
    完整
    -0.08
    chapter
    -0.08
    beat
    -0.08
    flow
    -0.08
     mover
    -0.08
    POSITIVE LOGITS
    色色
    0.19
    色
    0.16
     色
    0.14
     اللون
    0.14
     оттен
    0.14
    黃色
    0.14
    調
    0.14
    色视频
    0.13
    색
    0.13
    调
    0.12
    Activations Density 0.013%

    No Known Activations