© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110844
    Prev
    Next
    INDEX
    Explanations

    policies

    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
     Sele
    -0.08
     څو
    -0.08
    ané
    -0.08
    .variant
    -0.07
     Ricky
    -0.07
     ਪੁ
    -0.07
     Microsoft's
    -0.07
    alı
    -0.07
    -Württemberg
    -0.07
     Deco
    -0.07
    POSITIVE LOGITS
    496
    0.08
     â
    0.08
     eel
    0.08
    533
    0.08
    迎
    0.08
    _dyn
    0.07
    োল
    0.07
     evolve
    0.07
     эв
    0.07
    GLOBALS
    0.07
    Activations Density 0.054%

    No Known Activations