© 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. 19-RESID-POST-AA
    11. 103006
    Prev
    Next
    INDEX
    Explanations

    People's names and statements

    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
     if
    -0.10
    它
    -0.09
    。如果
    -0.09
     комбина
    -0.09
    ١
    -0.09
    ٩
    -0.09
     यदि
    -0.09
     قالب
    -0.09
     જેથી
    -0.09
     awọn
    -0.09
    POSITIVE LOGITS
     complained
    0.18
     responded
    0.18
     began
    0.17
     announced
    0.17
     apologized
    0.17
     reportedly
    0.16
     warned
    0.16
     announces
    0.16
     refused
    0.16
     took
    0.15
    Activations Density 0.228%

    No Known Activations