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. 11-RESID-POST-AA
    6. 11843
    Prev
    Next
    INDEX
    Explanations

    target

    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
     raport
    -0.08
     ferment
    -0.08
     recognise
    -0.08
     surf
    -0.08
     proté
    -0.07
     praxis
    -0.07
     Options
    -0.07
     illum
    -0.07
     prezent
    -0.07
     ilumin
    -0.07
    POSITIVE LOGITS
     gewe
    0.08
     elephants
    0.08
     lak
    0.08
     hann
    0.08
    वे
    0.07
    $con
    0.07
     lull
    0.07
    /ajax
    0.07
     loogu
    0.07
     elephant
    0.07
    Activations Density 0.003%

    No Known Activations