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

    Neuronpedia

    APICircuit 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. 12967
    Prev
    Next
    INDEX
    Explanations

    ExtJS

    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
    。そして
    -0.07
    ierend
    -0.07
    acar
    -0.07
    वर
    -0.07
    aal
    -0.07
     тя
    -0.07
    arry
    -0.07
    яж
    -0.07
     парамет
    -0.07
     pegg
    -0.07
    POSITIVE LOGITS
    fle
    0.08
     distal
    0.08
    Fabric
    0.08
     Shortly
    0.08
     föret
    0.08
    حض
    0.08
     Subscribe
    0.08
    પૂ
    0.08
    ણે
    0.07
    -----------↵
    0.07
    Activations Density 0.001%

    No Known Activations