© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48206
    Prev
    Next
    INDEX
    Explanations

    lad

    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
    .warn
    -0.08
    455
    -0.07
     mám
    -0.07
    .gz
    -0.07
    จี
    -0.07
    ம்ப
    -0.07
    ç
    -0.07
     manj
    -0.07
    زار
    -0.07
    ეტ
    -0.07
    POSITIVE LOGITS
    le
    0.13
    urée
    0.10
    (le
    0.10
    yleft
    0.08
    ishly
    0.08
    rao
    0.08
    duk
    0.08
    du
    0.08
    онь
    0.08
    yl
    0.08
    Activations Density 0.001%

    No Known Activations