Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44451
    Prev
    Next
    INDEX
    Explanations

    SQL database

    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
    Resolvers
    -0.09
     assister
    -0.08
    XT
    -0.08
     табылады
    -0.07
    ọwọ
    -0.07
    สอง
    -0.07
     rencontr
    -0.07
     Crian
    -0.07
    里的
    -0.07
    ciąż
    -0.07
    POSITIVE LOGITS
     설치
    0.08
     proc
    0.08
     installation
    0.08
     installs
    0.08
     Fortress
    0.08
     bege
    0.07
     WHO
    0.07
     GBP
    0.07
     atract
    0.07
     instalação
    0.07
    Activations Density 0.004%

    No Known Activations