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. 12168
    Prev
    Next
    INDEX
    Explanations

    gold

    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
     holog
    -0.08
     Shiva
    -0.08
    hamed
    -0.08
    _cell
    -0.08
    hv
    -0.08
    approve
    -0.07
    Stored
    -0.07
     Ariana
    -0.07
     Corporate
    -0.07
    hout
    -0.07
    POSITIVE LOGITS
     searches
    0.09
    _SEARCH
    0.09
     upr
    0.09
    Cape
    0.08
    	search
    0.08
     teren
    0.08
     搜
    0.08
     araştır
    0.08
     북
    0.08
     sucht
    0.08
    Activations Density 0.004%

    No Known Activations