© 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. 44728
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
    (custom
    -0.08
     które
    -0.07
    .linear
    -0.07
    (er
    -0.07
     tę
    -0.07
    _Vector
    -0.07
     komunit
    -0.07
     respectively
    -0.07
     indie
    -0.07
     "//
    -0.07
    POSITIVE LOGITS
     荣
    0.09
    Negative
    0.08
     Negative
    0.08
     सत्ता
    0.08
     Rav
    0.08
    API
    0.08
    荣耀
    0.08
     Positive
    0.07
     Guill
    0.07
    兽
    0.07
    Activations Density 0.002%

    No Known Activations