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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 77284
    Prev
    Next
    INDEX
    Explanations

    Software installation instructions

    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
     фон
    -0.08
    μμ
    -0.08
     lähe
    -0.08
     Basa
    -0.08
    achtig
    -0.08
    093
    -0.08
    stru
    -0.08
    φων
    -0.08
     overloaded
    -0.08
     stevige
    -0.08
    POSITIVE LOGITS
    安装
    0.13
     installiert
    0.12
    -installed
    0.12
    -install
    0.11
     설치
    0.11
    .install
    0.11
     instal
    0.11
     installieren
    0.11
    _install
    0.11
     installation
    0.11
    Activations Density 0.014%

    No Known Activations