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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129052
    Prev
    Next
    INDEX
    Explanations

    hydrophobicity/hydrophilicity

    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
     vows
    -0.08
     delegated
    -0.07
     resigned
    -0.07
     RVA
    -0.07
     Cumberland
    -0.07
     folded
    -0.07
    Opened
    -0.07
    nemen
    -0.07
     patent
    -0.07
    Industry
    -0.07
    POSITIVE LOGITS
     insensitive
    0.09
     tierra
    0.09
     ايس
    0.08
    ophobic
    0.08
    湿
    0.08
     aard
    0.08
     repell
    0.08
     heath
    0.08
     carbohydrates
    0.08
     affin
    0.08
    Activations Density 0.004%

    No Known Activations