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. 112189
    Prev
    Next
    INDEX
    Explanations

    quote character

    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
    Hashtable
    -0.09
     Hashtable
    -0.08
    Passed
    -0.08
    ились
    -0.08
     gye
    -0.07
     toda
    -0.07
     uter
    -0.07
    Ledger
    -0.07
    Concurrent
    -0.07
     linge
    -0.07
    POSITIVE LOGITS
     Anything
    0.11
     بأنها
    0.09
    ρη
    0.08
    Anything
    0.08
    ductor
    0.08
     بأنه
    0.08
    حية
    0.08
    что
    0.08
     мес
    0.08
    ٹھ
    0.08
    Activations Density 0.003%

    No Known Activations