© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110496
    Prev
    Next
    INDEX
    Explanations

    planetary atmospheres

    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
     даты
    -0.08
     дос
    -0.08
    iley
    -0.08
     groeps
    -0.08
     croche
    -0.08
     genius
    -0.08
     obchod
    -0.08
     სა
    -0.08
     мәх
    -0.08
    爷
    -0.08
    POSITIVE LOGITS
    Atmos
    0.11
     Atmospheric
    0.10
     atmosphere
    0.10
     atmospheric
    0.10
     breathable
    0.10
    空气
    0.09
     Atmos
    0.09
     inhabitants
    0.09
     gases
    0.09
     nitrogen
    0.09
    Activations Density 0.007%

    No Known Activations