© 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. 49203
    Prev
    Next
    INDEX
    Explanations

    -cons

    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
    RE
    -0.08
     steigen
    -0.08
     pollut
    -0.08
     лечении
    -0.08
     lept
    -0.07
    rological
    -0.07
     zašt
    -0.07
     stres
    -0.07
    coes
    -0.07
    logen
    -0.07
    POSITIVE LOGITS
    成年人
    0.09
    老人
    0.09
     answered
    0.09
     Apk
    0.08
     Möglichkeit
    0.08
    еспондент
    0.08
    、人
    0.08
     Mensch
    0.08
    enting
    0.08
     человека
    0.08
    Activations Density 0.001%

    No Known Activations