© 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. 11-RESID-POST-AA
    11. 44303
    Prev
    Next
    INDEX
    Explanations

    dialogue

    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
     chó
    -0.09
     należy
    -0.09
     имеется
    -0.09
     بواسطة
    -0.08
    akash
    -0.08
     succes
    -0.08
     fars
    -0.08
     ggf
    -0.08
     bardzo
    -0.08
     Wik
    -0.08
    POSITIVE LOGITS
    ですね
    0.11
    りまして
    0.10
    —or
    0.10
    —you
    0.10
     folks
    0.09
    ’ve
    0.09
    ’ll
    0.09
     justement
    0.09
    ……”↵↵
    0.09
     vocês
    0.09
    Activations Density 0.027%

    No Known Activations