© 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. 1316
    Prev
    Next
    INDEX
    Explanations

    .Length

    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
    asta
    -0.07
     товари
    -0.07
     asal
    -0.07
     �
    -0.07
    桶
    -0.07
     Camden
    -0.07
     unexpl
    -0.07
    fiber
    -0.07
    �
    -0.07
     ped
    -0.07
    POSITIVE LOGITS
     optimized
    0.08
     resil
    0.07
     Banque
    0.07
     Ani
    0.07
     volatile
    0.07
     Matt
    0.07
     pyr
    0.07
    optimized
    0.07
     пес
    0.07
    elligence
    0.07
    Activations Density 0.001%

    No Known Activations