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. 53798
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     पैसा
    -0.09
     деньги
    -0.08
    があります
    -0.08
     красивые
    -0.08
     fights
    -0.07
     drinking
    -0.07
     плох
    -0.07
     messed
    -0.07
    preuves
    -0.07
    AMA
    -0.07
    POSITIVE LOGITS
     delectable
    0.13
     sämtliche
    0.12
     esteemed
    0.12
     commencing
    0.12
     pertinent
    0.12
     requisite
    0.12
     merely
    0.11
     pertaining
    0.11
     myriad
    0.11
     mere
    0.10
    Activations Density 1.410%

    No Known Activations