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. 60437
    Prev
    Next
    INDEX
    Explanations

    MX

    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
    hens
    -0.08
     MK
    -0.08
     complied
    -0.08
     etk
    -0.08
    akn
    -0.08
     inertia
    -0.07
    黄
    -0.07
    》。
    -0.07
    athan
    -0.07
     niile
    -0.07
    POSITIVE LOGITS
    iped
    0.09
    ู
    0.09
     क्रम
    0.08
     Priority
    0.08
     prioridad
    0.08
    0.08
     جودة
    0.08
    Ranking
    0.08
     جذ
    0.07
    .priority
    0.07
    Activations Density 0.001%

    No Known Activations