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. 48759
    Prev
    Next
    INDEX
    Explanations

    reports

    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
     музыка
    -0.08
    ierig
    -0.07
    文明
    -0.07
     cred
    -0.07
     arrangement
    -0.07
    .asarray
    -0.07
     utens
    -0.07
    SAT
    -0.07
     swimmer
    -0.07
     seat
    -0.07
    POSITIVE LOGITS
    年度
    0.14
     annuel
    0.12
     annually
    0.12
     Annual
    0.12
    最新版
    0.11
     annual
    0.11
     annuelle
    0.11
     ஆண்டு
    0.11
     jährlich
    0.11
     لعام
    0.10
    Activations Density 0.027%

    No Known Activations