Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97161
    Prev
    Next
    INDEX
    Explanations

    Ac

    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
    спорт
    -0.09
    اسى
    -0.09
    肃
    -0.08
    ścią
    -0.08
    дор
    -0.08
    .sb
    -0.08
    nier
    -0.08
     surn
    -0.08
     puni
    -0.08
    刊
    -0.08
    POSITIVE LOGITS
    et
    0.12
    eto
    0.09
    etic
    0.09
    ét
    0.09
    etas
    0.08
    é
    0.08
    am
    0.08
    ouli
    0.08
    etos
    0.08
    (et
    0.08
    Activations Density 0.001%

    No Known Activations