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. 102743
    Prev
    Next
    INDEX
    Explanations

    math proofs

    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
     pandem
    -0.09
     obviously
    -0.08
    ಣ್ಣ
    -0.08
     graduate
    -0.07
     admittedly
    -0.07
    手
    -0.07
     obviamente
    -0.07
     handed
    -0.07
     таком
    -0.07
     QA
    -0.07
    POSITIVE LOGITS
    Mir
    0.08
     demonstrates
    0.08
     Cip
    0.08
    approximately
    0.08
    gne
    0.08
     approximately
    0.07
     Skin
    0.07
     diá
    0.07
     অন্যতম
    0.07
     जाइ
    0.07
    Activations Density 0.054%

    No Known Activations