© 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. 64972
    Prev
    Next
    INDEX
    Explanations

    Translation/Chatbot interactions

    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
     DARK
    -0.08
    dark
    -0.08
     chairman
    -0.08
    аман
    -0.08
     dark
    -0.08
    .portlet
    -0.07
     предприятий
    -0.07
     лиценз
    -0.07
    (hash
    -0.07
     artis
    -0.07
    POSITIVE LOGITS
     pronunciation
    0.16
     grammatical
    0.16
    Grammar
    0.16
     IELTS
    0.16
     Grammar
    0.15
     grammar
    0.15
     اللغة
    0.14
     vocabulary
    0.14
    英语
    0.14
     Vocabulary
    0.14
    Activations Density 0.150%

    No Known Activations