© 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. 63102
    Prev
    Next
    INDEX
    Explanations

    number sequences and codes

    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
     плат
    -0.09
     Natalia
    -0.08
    。如
    -0.08
    ，会
    -0.08
     Distributor
    -0.08
    ，据
    -0.08
     Shim
    -0.08
     pô
    -0.07
    еди
    -0.07
     Biel
    -0.07
    POSITIVE LOGITS
    XXXXXXXX
    0.07
    base
    0.07
     milk
    0.07
     suck
    0.07
    -ID
    0.07
    smith
    0.07
     ice
    0.07
     thes
    0.07
    ave
    0.07
    stuff
    0.07
    Activations Density 0.024%

    No Known Activations