© 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. 12800
    Prev
    Next
    INDEX
    Explanations

    :

    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
    에서는
    -0.09
    .Xtra
    -0.08
     программ
    -0.08
     americana
    -0.08
    었습니다
    -0.08
     chưa
    -0.08
     Tut
    -0.08
     Dat
    -0.08
    아이
    -0.07
     normative
    -0.07
    POSITIVE LOGITS
     unmistak
    0.08
     sor
    0.08
     feas
    0.08
     steward
    0.08
     चाहते
    0.07
     eradicate
    0.07
     пот
    0.07
     Jem
    0.07
     जानते
    0.07
    ਰਾ
    0.07
    Activations Density 0.025%

    No Known Activations