© 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. 11-RESID-POST-AA
    11. 31168
    Prev
    Next
    INDEX
    Explanations

    too late/then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relate
    -0.08
    纪录
    -0.08
     apply
    -0.07
     seem
    -0.07
    צלחה
    -0.07
     Birch
    -0.07
    哦
    -0.07
     inherit
    -0.07
    ird
    -0.07
     respond
    -0.07
    POSITIVE LOGITS
     уже
    0.11
     bereits
    0.10
     spät
    0.10
     déjà
    0.10
     देर
    0.10
     �
    0.10
     позд
    0.10
     вже
    0.09
     утра
    0.09
     arriva
    0.09
    Activations Density 0.015%

    No Known Activations