© 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. 47900
    Prev
    Next
    INDEX
    Explanations

    Negations and conditionals

    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
    グ
    -0.08
     グ
    -0.08
    합니다
    -0.07
     resumes
    -0.07
    ಗ್ರ
    -0.07
     curves
    -0.07
    zcza
    -0.07
    ಳ
    -0.07
    _globals
    -0.07
    oders
    -0.07
    POSITIVE LOGITS
     varsa
    0.10
    이면
    0.10
     tiver
    0.09
    െങ്കിൽ
    0.09
     doubts
    0.09
     doubt
    0.09
     হলে
    0.09
     хоть
    0.09
     eenmaal
    0.08
    െങ്ക
    0.08
    Activations Density 0.115%

    No Known Activations