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. 53069
    Prev
    Next
    INDEX
    Explanations

    amine

    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
     ekstrem
    -0.08
    /i
    -0.08
     Entity
    -0.08
     pessoal
    -0.08
    .bar
    -0.07
     Strategies
    -0.07
     Emery
    -0.07
    жи
    -0.07
    Credentials
    -0.07
    ਿਹ
    -0.07
    POSITIVE LOGITS
    裂
    0.08
     decline
    0.08
     msm
    0.08
     ছিল
    0.08
     burden
    0.08
     bani
    0.07
     broadband
    0.07
     analyst
    0.07
    iden
    0.07
     seized
    0.07
    Activations Density 0.000%

    No Known Activations