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. 88125
    Prev
    Next
    INDEX
    Explanations

    Networking protocols

    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
     davanti
    -0.09
     sosp
    -0.08
     kans
    -0.08
     wacht
    -0.08
    Browsing
    -0.08
     நிலைய
    -0.08
    -variable
    -0.08
     niets
    -0.08
    ("").
    -0.08
     niks
    -0.08
    POSITIVE LOGITS
    воз
    0.08
    LLU
    0.08
     Prin
    0.07
    /models
    0.07
    ילות
    0.07
    شارك
    0.07
    иск
    0.07
     liefern
    0.07
     colspan
    0.07
     section
    0.07
    Activations Density 0.074%

    No Known Activations