© 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. 96488
    Prev
    Next
    INDEX
    Explanations

    text

    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
    кова
    -0.09
     yard
    -0.08
     Yard
    -0.08
    cara
    -0.08
    കാര്യ
    -0.07
    ків
    -0.07
     karma
    -0.07
    집
    -0.07
    \classes
    -0.07
     девуш
    -0.07
    POSITIVE LOGITS
    {o
    0.09
     Antrag
    0.08
     Ane
    0.08
    rek
    0.08
     sā
    0.08
     Plenty
    0.08
    ែង
    0.08
     bleiben
    0.07
    ریان
    0.07
    —they
    0.07
    Activations Density 0.001%

    No Known Activations