© 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. 50630
    Prev
    Next
    INDEX
    Explanations

    Ge

    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
     org
    -0.09
    org
    -0.08
     slu
    -0.08
    	org
    -0.08
     passat
    -0.08
    _org
    -0.08
     bal
    -0.08
    นาย
    -0.08
    762
    -0.08
    .org
    -0.07
    POSITIVE LOGITS
    om
    0.15
    ometric
    0.14
    ographical
    0.14
    ométr
    0.13
    ometr
    0.13
    gevens
    0.12
    omorphic
    0.12
    othermal
    0.12
    ographically
    0.11
    legen
    0.11
    Activations Density 0.003%

    No Known Activations