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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19149
    Prev
    Next
    INDEX
    Explanations

    describing code features

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     haddii
    -0.09
    Lorsque
    -0.08
    okr
    -0.08
     candidature
    -0.08
    chern
    -0.08
    Wenn
    -0.08
    wor
    -0.07
    mongodb
    -0.07
    ocat
    -0.07
    orkar
    -0.07
    POSITIVE LOGITS
     perhaps
    0.14
     quizás
    0.10
     This
    0.10
     Perhaps
    0.10
     talvez
    0.09
    perhaps
    0.09
                       
    0.09
     maybe
    0.09
     several
    0.09
     Multiple
    0.09
    Activations Density 0.004%

    No Known Activations