© 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. 23-RESID-POST-AA
    11. 96468
    Prev
    Next
    INDEX
    Explanations

    od

    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
     simulate
    -0.08
    ució
    -0.08
     propi
    -0.08
     अनु
    -0.08
    datatable
    -0.07
     Dino
    -0.07
    ,o
    -0.07
    ansı
    -0.07
    U
    -0.07
     Sim
    -0.07
    POSITIVE LOGITS
    gr
    0.08
    	gr
    0.08
    .Gr
    0.08
     Gr
    0.07
    Gr
    0.07
    mdb
    0.07
    mpl
    0.07
     Raja
    0.07
     grø
    0.07
    m
    0.07
    Activations Density 0.022%

    No Known Activations