© 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. 48843
    Prev
    Next
    INDEX
    Explanations

    worms

    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
    擊
    -0.09
    ICP备
    -0.09
     BELOW
    -0.08
    emies
    -0.08
     scuola
    -0.08
     wetenschap
    -0.08
    cours
    -0.08
     schools
    -0.08
     container
    -0.07
     impedance
    -0.07
    POSITIVE LOGITS
    lumbr
    0.11
     medicinal
    0.09
     sangu
    0.09
     lug
    0.08
     regenerate
    0.08
     deposit
    0.08
     ribbon
    0.08
     Lum
    0.08
     le
    0.08
    lug
    0.08
    Activations Density 0.003%

    No Known Activations