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. 96991
    Prev
    Next
    INDEX
    Explanations

    778

    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
    ucky
    -0.09
    Fw
    -0.08
    惠
    -0.08
    ړه
    -0.08
    BOOT
    -0.07
     Zhu
    -0.07
     deleting
    -0.07
    ړې
    -0.07
    敏
    -0.07
    fw
    -0.07
    POSITIVE LOGITS
    151
    0.09
    าชน
    0.08
    ען
    0.07
    ത്തെ
    0.07
    (depth
    0.07
     अवध
    0.07
    .depth
    0.07
    (parsed
    0.07
     עת
    0.07
     ఉ
    0.07
    Activations Density 0.000%

    No Known Activations