© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2751
    Prev
    Next
    INDEX
    Explanations

    י

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seine
    -0.11
     Machines
    -0.08
    iphone
    -0.08
     Pero
    -0.08
    .operation
    -0.07
     touchdown
    -0.07
     Bott
    -0.07
     MACHINE
    -0.07
       ↵
    -0.07
     carbon
    -0.07
    POSITIVE LOGITS
     Highland
    0.08
    "<<
    0.08
    �
    0.07
     आर
    0.07
     срод
    0.07
    �
    0.07
     decorator
    0.07
     sozial
    0.07
    �
    0.07
     تیار
    0.07
    Activations Density 0.000%

    No Known Activations