© 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. 3022
    Prev
    Next
    INDEX
    Explanations

    الوقت

    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
    かな
    -0.08
    抽
    -0.07
    اده
    -0.07
     hir
    -0.07
     woj
    -0.07
    mme
    -0.07
     BP
    -0.07
     cro
    -0.07
     hym
    -0.07
     syll
    -0.07
    POSITIVE LOGITS
     pun
    0.09
     sifat
    0.08
     времена
    0.08
    went
    0.08
    -même
    0.08
    into
    0.08
     Sieg
    0.07
    heated
    0.07
    killer
    0.07
     tit
    0.07
    Activations Density 0.018%

    No Known Activations