© 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. 23-RESID-POST-AA
    11. 51680
    Prev
    Next
    INDEX
    Explanations

    MP

    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
    criptor
    -0.09
     TV
    -0.08
     šest
    -0.08
    animate
    -0.08
     Palacio
    -0.08
     TVs
    -0.08
     June
    -0.08
     televisions
    -0.08
    严格
    -0.08
     ТВ
    -0.08
    POSITIVE LOGITS
    31
    0.10
    314
    0.09
    394
    0.09
    312
    0.09
    EW
    0.08
    32
    0.08
    One
    0.08
     mell
    0.08
    251
    0.08
     Alem
    0.08
    Activations Density 0.001%

    No Known Activations