© 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. 44520
    Prev
    Next
    INDEX
    Explanations

    coordinate axes manipulation

    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
     venom
    -0.09
    ्लेष
    -0.08
     gourmet
    -0.08
    れて
    -0.07
     :).
    -0.07
     Kū
    -0.07
     noct
    -0.07
    (reverse
    -0.07
     ве
    -0.07
    heen
    -0.07
    POSITIVE LOGITS
     വീട
    0.09
    轴
    0.08
     ausgestattet
    0.08
    _masks
    0.08
     ಮನೆ
    0.08
     RENT
    0.08
    emma
    0.08
    တို
    0.08
     வீட்ட
    0.07
    robes
    0.07
    Activations Density 0.001%

    No Known Activations