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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 88126
    Prev
    Next
    INDEX
    Explanations

    Question words

    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
     उद्योग
    -0.08
     leves
    -0.08
     स्वाद
    -0.08
    impin
    -0.08
     locksmith
    -0.08
     basics
    -0.08
     unmanaged
    -0.07
     thunderstorms
    -0.07
     cita
    -0.07
     academ
    -0.07
    POSITIVE LOGITS
    是否
    0.13
     여부
    0.13
     是否
    0.13
     Yes
    0.11
     apakah
    0.11
     yes
    0.11
    Yes
    0.10
     آیا
    0.10
     האם
    0.10
    _yes
    0.10
    Activations Density 0.025%

    No Known Activations