© 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. 3-RESID-POST-AA
    11. 2798
    Prev
    Next
    INDEX
    Explanations

    str

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     epidemi
    -0.08
     Latin
    -0.08
     alas
    -0.07
     empirical
    -0.07
     evidence
    -0.07
     terreno
    -0.07
     Ne
    -0.07
     blockade
    -0.07
    utile
    -0.07
     empir
    -0.07
    POSITIVE LOGITS
     Igor
    0.08
    (prefix
    0.07
    works
    0.07
     vors
    0.07
    éraux
    0.07
    ossi
    0.07
    kope
    0.07
    cook
    0.07
     Yar
    0.07
     achieves
    0.07
    Activations Density 0.001%

    No Known Activations