© 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. 51890
    Prev
    Next
    INDEX
    Explanations

    "

    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
     majest
    -0.08
     CDs
    -0.08
    cd
    -0.07
    fstream
    -0.07
    _globals
    -0.07
    Globals
    -0.07
    тим
    -0.07
     atom
    -0.07
     katastro
    -0.07
    анги
    -0.07
    POSITIVE LOGITS
     Eastern
    0.11
    Eastern
    0.10
     eastern
    0.10
     woo
    0.09
    “He
    0.09
     banyere
    0.08
     Western
    0.08
    0.08
    -outs
    0.08
     hoʻop
    0.08
    Activations Density 0.002%
    No Known Activations