Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 30765
    Prev
    Next
    INDEX
    Explanations

    feet

    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
     Wy
    -0.09
     borrower
    -0.08
     निर्म
    -0.08
     dels
    -0.08
    ’él
    -0.08
    Wy
    -0.08
     loci
    -0.07
     nkw
    -0.07
     newsp
    -0.07
    成交
    -0.07
    POSITIVE LOGITS
     glob
    0.08
     cardi
    0.08
    ાદ
    0.08
     pog
    0.08
    玩
    0.07
    ора
    0.07
     Sad
    0.07
    ाद
    0.07
    /mobile
    0.07
     immobil
    0.07
    Activations Density 0.010%

    No Known Activations