© 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. 51045
    Prev
    Next
    INDEX
    Explanations

    Legal and academic texts

    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
     kupa
    -0.09
     pě
    -0.09
    (*
    -0.09
    	act
    -0.08
    াৰী
    -0.08
     ot
    -0.08
     nomb
    -0.08
    acti
    -0.08
     дру
    -0.08
     kumu
    -0.08
    POSITIVE LOGITS
     Rezension
    0.08
     Neste
    0.08
     pasada
    0.07
    0.07
     Compress
    0.07
    erialize
    0.07
    .instagram
    0.07
     Crypto
    0.07
     Cr
    0.07
     Dann
    0.07
    Activations Density 0.000%
    No Known Activations