© 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. 6365
    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
    Church
    -0.09
    ателям
    -0.08
     Threads
    -0.08
    Gir
    -0.08
    church
    -0.08
    kins
    -0.08
    stige
    -0.08
     stjórn
    -0.08
    دارية
    -0.08
    ledad
    -0.08
    POSITIVE LOGITS
     SQ
    0.09
     $\
    0.09
     \
    0.09
     raíz
    0.09
     APR
    0.08
     â
    0.08
    _ROOT
    0.08
     TORT
    0.08
     ROOT
    0.08
    $\
    0.08
    Activations Density 0.032%

    No Known Activations