© 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. 110447
    Prev
    Next
    INDEX
    Explanations

    E

    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
     निर्देशक
    -0.08
    refer
    -0.08
     التد
    -0.08
     refr
    -0.07
     refinement
    -0.07
     pied
    -0.07
    _De
    -0.07
     revised
    -0.07
    (pid
    -0.07
    resultado
    -0.07
    POSITIVE LOGITS
    -create
    0.09
    Device
    0.09
    .Device
    0.09
    .device
    0.08
    _device
    0.08
     oluştur
    0.08
    .Game
    0.08
    belief
    0.08
    #create
    0.08
    _create
    0.08
    Activations Density 0.000%

    No Known Activations