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. 65138
    Prev
    Next
    INDEX
    Explanations

    gritting teeth/labor pain

    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
     Natal
    -0.08
     Dal
    -0.08
    istler
    -0.07
     Fc
    -0.07
     plen
    -0.07
     Fast
    -0.07
    ík
    -0.07
    _rates
    -0.07
     Rates
    -0.07
     Prot
    -0.07
    POSITIVE LOGITS
     zetten
    0.09
     моря
    0.09
     ყურადღ
    0.09
    ️⃣
    0.09
    -hearted
    0.09
     მიზ
    0.09
    ვის
    0.08
     ზღ
    0.08
     ხმ
    0.08
     საკუთ
    0.08
    Activations Density 0.001%

    No Known Activations