© 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. 11-RESID-POST-AA
    11. 78098
    Prev
    Next
    INDEX
    Explanations

    Unity camera controls/movement

    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
     Stamp
    -0.09
    stamp
    -0.09
    Stamp
    -0.09
    Spirit
    -0.08
     stamp
    -0.08
     stamps
    -0.08
     festive
    -0.08
     Ambul
    -0.07
    _stamp
    -0.07
     máquinas
    -0.07
    POSITIVE LOGITS
     anger
    0.09
    Yaw
    0.09
     الرأس
    0.09
     rage
    0.09
     ორივ
    0.09
     acos
    0.09
     revenge
    0.09
    იარ
    0.09
     yaw
    0.09
    亂倫
    0.08
    Activations Density 0.002%

    No Known Activations