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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 131017
    Prev
    Next
    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DOM
    -0.08
    .DOM
    -0.08
     मरीज
    -0.07
    ighty
    -0.07
     взгляд
    -0.07
     responses
    -0.07
    Domin
    -0.07
    午後
    -0.07
     bree
    -0.07
    鹰
    -0.07
    POSITIVE LOGITS
     মূল
    0.10
     اصلی
    0.08
     coined
    0.08
     ছিল
    0.08
     Writable
    0.08
    (enc
    0.08
     Zi
    0.07
     없는
    0.07
    ార్థ
    0.07
     hassle
    0.07
    Activations Density 0.011%

    No Known Activations