© 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. 23-RESID-POST-AA
    11. 49118
    Prev
    Next
    INDEX
    Explanations

    parabolas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idges
    -0.09
     ibikorwa
    -0.08
    Horiz
    -0.08
     глазами
    -0.08
     عملية
    -0.08
     عنصر
    -0.08
    았다
    -0.08
     northeastern
    -0.08
     omhoog
    -0.08
    上下
    -0.08
    POSITIVE LOGITS
    -opening
    0.13
     facing
    0.12
    -point
    0.11
    -facing
    0.11
    Facing
    0.11
     Facing
    0.11
    -sl
    0.10
     pointing
    0.09
    -oriented
    0.09
    posing
    0.09
    Activations Density 0.004%

    No Known Activations