© 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. 30442
    Prev
    Next
    INDEX
    Explanations

    radius

    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
    uang
    -0.08
    arım
    -0.08
     iro
    -0.07
    emo
    -0.07
     Maa
    -0.07
     üstünlik
    -0.07
    caire
    -0.07
     haunt
    -0.07
     YC
    -0.07
    šla
    -0.07
    POSITIVE LOGITS
     perpendicular
    0.10
    _len
    0.09
     линия
    0.08
    pendicular
    0.07
    forming
    0.07
     русского
    0.07
    今回
    0.07
    宗
    0.07
     הראשון
    0.07
     oriented
    0.07
    Activations Density 0.009%

    No Known Activations