© 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. 11-RESID-POST-AA
    11. 94872
    Prev
    Next
    INDEX
    Explanations

    Memory mapping

    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
     Systems
    -0.08
     mentions
    -0.07
     jsem
    -0.07
    详
    -0.07
     কার্য
    -0.07
     nói
    -0.07
     tí
    -0.07
    systems
    -0.07
     thrust
    -0.07
     possessions
    -0.07
    POSITIVE LOGITS
    овано
    0.08
    ованных
    0.08
     flagged
    0.08
    ованы
    0.08
    Execute
    0.08
    /un
    0.08
    0.07
     соглаш
    0.07
     Flag
    0.07
    uplicate
    0.07
    Activations Density 0.001%
    No Known Activations