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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 884
    Prev
    Next
    INDEX
    Explanations

    Isabelle

    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
     kuma
    -0.08
     Анал
    -0.08
     ਜ
    -0.07
    hall
    -0.07
    。不
    -0.07
    抵
    -0.07
     elephant
    -0.07
     Squares
    -0.07
     distr
    -0.07
     Stevie
    -0.07
    POSITIVE LOGITS
     thre
    0.08
    ĺ
    0.08
    �
    0.07
    ŝ
    0.07
     �
    0.07
    .Bean
    0.07
     Hastings
    0.07
    .asm
    0.07
     Blake
    0.07
     Oss
    0.07
    Activations Density 0.001%

    No Known Activations