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. 112224
    Prev
    Next
    INDEX
    Explanations

    pollutants and emissions

    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
     undefeated
    -0.07
    ase
    -0.07
     unbeaten
    -0.07
    Encoder
    -0.07
    undle
    -0.07
     spacer
    -0.07
    Oo
    -0.07
     MG
    -0.07
    Responder
    -0.07
     bson
    -0.07
    POSITIVE LOGITS
     soot
    0.10
     emisión
    0.09
     ash
    0.08
     Laurel
    0.08
     emissions
    0.08
     combustion
    0.08
     emissão
    0.08
    (sockfd
    0.08
    IFIC
    0.08
    煤
    0.08
    Activations Density 0.007%

    No Known Activations