© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30461
    Prev
    Next
    INDEX
    Explanations

    assignments of items to places

    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
    Allowance
    -0.08
     clocks
    -0.08
    handa
    -0.08
    erseits
    -0.08
     trembling
    -0.08
    waan
    -0.08
    kega
    -0.08
    �ర్
    -0.08
     iterations
    -0.07
    ക്കും
    -0.07
    POSITIVE LOGITS
     annex
    0.09
     принадлеж
    0.08
    ospital
    0.08
     asign
    0.08
     assigns
    0.08
     assignments
    0.08
    plac
    0.08
    belongs
    0.08
    unting
    0.07
    assign
    0.07
    Activations Density 0.026%

    No Known Activations