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. 49203
    Prev
    Next
    INDEX
    Explanations

    website cookies

    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
     keen
    -0.08
    Keith
    -0.08
    THON
    -0.08
     Keith
    -0.07
    Ст
    -0.07
    анні
    -0.07
     shale
    -0.07
     whatever
    -0.07
     Moy
    -0.07
    Rewards
    -0.07
    POSITIVE LOGITS
    -op
    0.08
     фик
    0.08
    äd
    0.08
    出去
    0.08
     vote
    0.08
    -person
    0.08
     ul
    0.07
     apellido
    0.07
     승인
    0.07
     vergadering
    0.07
    Activations Density 0.004%

    No Known Activations