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. 9024
    Prev
    Next
    INDEX
    Explanations

    章节

    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
    uestran
    -0.08
     Kommunikation
    -0.08
    \Query
    -0.08
    -soft
    -0.07
     QUERY
    -0.07
    vány
    -0.07
     Comunicación
    -0.07
     ausprobieren
    -0.07
    \Test
    -0.07
    ván
    -0.07
    POSITIVE LOGITS
     конце
    0.08
     અધ
    0.08
     Kapitel
    0.08
     naval
    0.07
     heter
    0.07
     sapp
    0.07
     wav
    0.07
    ​
    0.07
     department
    0.07
     thor
    0.07
    Activations Density 0.001%

    No Known Activations