© 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. 68156
    Prev
    Next
    INDEX
    Explanations

    personality descriptions

    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
     purchasers
    -0.09
     subtotal
    -0.08
     boleto
    -0.08
     상품
    -0.08
     деф
    -0.08
    betrag
    -0.08
     petro
    -0.08
     bundes
    -0.08
     centroid
    -0.08
     वितरण
    -0.07
    POSITIVE LOGITS
    。他
    0.11
     constantemente
    0.10
     constamment
    0.10
     constantly
    0.10
     항상
    0.09
     തന്റെ
    0.09
     tirelessly
    0.09
     کبھی
    0.09
     हमेशा
    0.09
     inquis
    0.09
    Activations Density 0.089%

    No Known Activations