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. 60028
    Prev
    Next
    INDEX
    Explanations

    Vue.js code

    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
     excav
    -0.09
     ніж
    -0.08
     ڪار
    -0.08
    -0.08
     чолов
    -0.08
    (CL
    -0.07
     performant
    -0.07
    eing
    -0.07
    ']]['
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Washington
    0.08
     Mass
    0.08
     recherchez
    0.08
    enna
    0.08
     몸
    0.08
     Metallic
    0.08
     Mohamed
    0.07
    ительное
    0.07
    ជ
    0.07
     Hb
    0.07
    Activations Density 0.000%

    No Known Activations