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. 12157
    Prev
    Next
    INDEX
    Explanations

    !=

    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
     commod
    -0.09
     mish
    -0.08
    �
    -0.08
     allies
    -0.08
     spill
    -0.08
     tě
    -0.08
     appris
    -0.08
    池
    -0.07
    Pools
    -0.07
    spill
    -0.07
    POSITIVE LOGITS
    empatan
    0.07
     тұрғын
    0.07
    Thanh
    0.07
    شنا
    0.07
    (sys
    0.07
    Sett
    0.07
     ultimately
    0.07
     boh
    0.07
    ENO
    0.07
    ńczy
    0.07
    Activations Density 0.001%

    No Known Activations