© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7960
    Prev
    Next
    INDEX
    Explanations

    code

    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
     பார்க்க
    -0.09
     Book
    -0.09
    Leather
    -0.09
     شورای
    -0.08
    :VC
    -0.08
     Cush
    -0.08
    _STD
    -0.08
    _book
    -0.08
     Suomen
    -0.08
     ket
    -0.08
    POSITIVE LOGITS
     diminu
    0.07
    (dictionary
    0.07
    (item
    0.07
    inye
    0.07
    (Dictionary
    0.07
     opposite
    0.07
    anam
    0.07
    contained
    0.07
     notamment
    0.07
    一句
    0.07
    Activations Density 0.000%

    No Known Activations