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. 43719
    Prev
    Next
    INDEX
    Explanations

    policy

    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
     boring
    -0.08
    ????????
    -0.08
    wart
    -0.07
     someday
    -0.07
     Ans
    -0.07
     TMP
    -0.07
     ca
    -0.07
     PCB
    -0.07
     definitive
    -0.07
     Tur
    -0.07
    POSITIVE LOGITS
     запрещ
    0.10
    规定
    0.10
     prohibits
    0.09
    禁止
    0.09
     মতে
    0.08
     పేర్క
    0.08
     forbid
    0.08
     zufolge
    0.08
     says
    0.08
    र्प
    0.08
    Activations Density 0.006%

    No Known Activations