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. 90222
    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_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KW
    -0.08
    kw
    -0.08
     Romantic
    -0.08
     topical
    -0.08
    鼓
    -0.08
    TR
    -0.07
     climate
    -0.07
    ема
    -0.07
     Matteo
    -0.07
     fantasy
    -0.07
    POSITIVE LOGITS
    -chave
    0.09
    wise
    0.09
     પરથી
    0.08
     apex
    0.08
    WISE
    0.08
     coordinates
    0.08
    -là
    0.08
     Coordinates
    0.08
    ાંક
    0.08
     graz
    0.08
    Activations Density 0.063%

    No Known Activations