© 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. 16719
    Prev
    Next
    INDEX
    Explanations

    for

    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
    wati
    -0.10
     также
    -0.09
    edik
    -0.09
     inoltre
    -0.09
    ilyen
    -0.09
     também
    -0.09
     також
    -0.09
    puru
    -0.09
    erus
    -0.08
    eň
    -0.08
    POSITIVE LOGITS
    的是
    0.11
     eher
    0.09
    Ext
    0.08
     uncontrolled
    0.08
     allgeme
    0.07
     textual
    0.07
     rather
    0.07
     ವಿಭ
    0.07
    तर
    0.07
    不同
    0.07
    Activations Density 0.038%

    No Known Activations