© 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. 876
    Prev
    Next
    INDEX
    Explanations

    Even

    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
     seal
    -0.08
     yal
    -0.07
    677
    -0.07
     ecology
    -0.07
     disent
    -0.07
     leadership
    -0.07
    -0.07
     Sainte
    -0.07
     hyperlink
    -0.07
    SW
    -0.07
    POSITIVE LOGITS
     BRO
    0.09
    CRI
    0.08
     PIC
    0.07
     عشر
    0.07
     Birch
    0.07
    Marco
    0.07
    这样的
    0.07
    続
    0.07
    [name
    0.07
    któ
    0.07
    Activations Density 0.026%
    No Known Activations