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. 97958
    Prev
    Next
    INDEX
    Explanations

    하

    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
    ring
    -0.08
     Abigail
    -0.08
    acency
    -0.08
    hoo
    -0.08
    icking
    -0.08
     Fri
    -0.08
    itional
    -0.07
    rings
    -0.07
    pedia
    -0.07
     Baseball
    -0.07
    POSITIVE LOGITS
    이
    0.12
    이라
    0.12
    ೈ
    0.11
    ाई
    0.10
    ード
    0.10
    이드
    0.10
    이버
    0.10
    트
    0.10
    イ
    0.09
    드
    0.09
    Activations Density 0.000%

    No Known Activations