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. 53320
    Prev
    Next
    INDEX
    Explanations

    squares

    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
     Lemon
    -0.08
     Finance
    -0.08
    .ts
    -0.08
    .service
    -0.08
    랙
    -0.08
    라인
    -0.07
     Arche
    -0.07
     HIV
    -0.07
     HTTPS
    -0.07
     Oscar
    -0.07
    POSITIVE LOGITS
    -thirds
    0.08
    Sa
    0.08
    sa
    0.08
    roots
    0.08
    Fem
    0.07
    itif
    0.07
    0.07
    eris
    0.07
    是多少
    0.07
    ىسى
    0.07
    Activations Density 0.009%

    No Known Activations