© 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. 15-RESID-POST-AA
    11. 16375
    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otros
    -0.09
     від
    -0.09
     آخر
    -0.08
    CERT
    -0.08
     outage
    -0.08
    (sec
    -0.08
     weiteren
    -0.08
    jenigen
    -0.08
     kez
    -0.07
     withd
    -0.07
    POSITIVE LOGITS
    mdash
    0.12
     perhaps
    0.10
    ndash
    0.09
    number
    0.09
    perhaps
    0.09
    ½
    0.09
     
    0.09
    whatever
    0.08
     zumindest
    0.08
    соз
    0.08
    Activations Density 0.062%

    No Known Activations