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. 60095
    Prev
    Next
    INDEX
    Explanations

    bees

    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
     commenting
    -0.09
     build
    -0.07
    (man
    -0.07
    -0.07
    abbing
    -0.07
    espresso
    -0.07
    landing
    -0.07
    imm
    -0.07
    (CL
    -0.07
     CL
    -0.07
    POSITIVE LOGITS
     پایان
    0.14
     തുടര
    0.13
     аяқ
    0.13
    继续
    0.13
     కొనసాగ
    0.13
     അവസാന
    0.12
     законч
    0.12
     खत्म
    0.12
     selesai
    0.12
     disappears
    0.12
    Activations Density 0.219%

    No Known Activations