© 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. 11-RESID-POST-AA
    11. 78867
    Prev
    Next
    INDEX
    Explanations

    C

    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
     خدمت
    -0.08
     نتائج
    -0.08
    (enabled
    -0.08
    yecto
    -0.07
     चुका
    -0.07
    <data
    -0.07
     <↵
    -0.07
    <Application
    -0.07
     >↵↵
    -0.07
    _mes
    -0.07
    POSITIVE LOGITS
    その他
    0.10
     その他
    0.09
    本人
    0.09
     antwort
    0.08
     และ
    0.08
    そして
    0.08
    rd
    0.08
    等等
    0.08
     sonst
    0.08
     downright
    0.08
    Activations Density 0.015%

    No Known Activations