© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6037
    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (if
    -0.12
    when
    -0.11
    if
    -0.10
    	when
    -0.10
    WHEN
    -0.09
     when
    -0.09
    izations
    -0.09
    "When
    -0.09
    ી�
    -0.09
    unless
    -0.09
    POSITIVE LOGITS
     Якщо
    0.10
    য
    0.10
     Если
    0.10
     Nếu
    0.10
     თუ
    0.10
    000
    0.09
    Як
    0.09
     ਜ
    0.09
    롭
    0.09
     ес
    0.08
    Activations Density 0.208%

    No Known Activations