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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18505
    Prev
    Next
    INDEX
    Explanations

    say "if"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ・・・。↵↵
    -0.08
     lawm
    -0.08
    orsunuz
    -0.08
    -ийн
    -0.08
     դեպի
    -0.07
    ansin
    -0.07
     რომელ
    -0.07
    、、、
    -0.07
    -steach
    -0.07
     თითქმის
    -0.07
    POSITIVE LOGITS
     if
    0.56
     nếu
    0.52
     jika
    0.52
     إذا
    0.52
     если
    0.51
     dacă
    0.50
     यदि
    0.50
     যদি
    0.49
     jeśli
    0.48
     якщо
    0.48
    Activations Density 0.961%

    No Known Activations