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. 65828
    Prev
    Next
    INDEX
    Explanations

    2

    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
     obej
    -0.07
    clipboard
    -0.07
    يته
    -0.07
    মাত্র
    -0.07
    ाले
    -0.07
     größere
    -0.07
    ої
    -0.07
     initialization
    -0.07
    まだ
    -0.07
    .sap
    -0.07
    POSITIVE LOGITS
    Pers
    0.08
     Bueno
    0.08
    ilin
    0.07
    anim
    0.07
     аромат
    0.07
    atim
    0.07
     tratt
    0.07
    훈
    0.07
     Tested
    0.07
    Qua
    0.07
    Activations Density 0.003%

    No Known Activations