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. 48950
    Prev
    Next
    INDEX
    Explanations

    cooling and refrigeration

    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
     UK
    -0.09
     GMP
    -0.09
     RM
    -0.08
     seis
    -0.08
    /USD
    -0.08
    reep
    -0.08
     CRS
    -0.08
     MPH
    -0.08
     PSD
    -0.08
     GD
    -0.08
    POSITIVE LOGITS
    });
    ↵
    0.08
    əl
    0.08
     vasit
    0.08
     neural
    0.08
    ức
    0.07
     tekenen
    0.07
    əsinin
    0.07
     recue
    0.07
     irin
    0.07
    }`).
    0.07
    Activations Density 0.002%

    No Known Activations