© 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. 68222
    Prev
    Next
    INDEX
    Explanations

    context

    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
     tipped
    -0.09
    精
    -0.08
     amie
    -0.08
    porta
    -0.07
     plantilla
    -0.07
     βά
    -0.07
     prayed
    -0.07
     পৃথ
    -0.07
    _friend
    -0.07
     μη
    -0.07
    POSITIVE LOGITS
     당시
    0.13
     prevailing
    0.12
     societal
    0.12
     geopolitical
    0.12
     political
    0.12
     milieu
    0.12
     socio
    0.11
     contempor
    0.11
     époque
    0.11
    'époque
    0.11
    Activations Density 0.039%

    No Known Activations