© 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. 19-RESID-POST-AA
    11. 102622
    Prev
    Next
    INDEX
    Explanations

    motion

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ħafna
    -0.09
    Provincia
    -0.09
     ukwuu
    -0.09
     proud
    -0.09
     taza
    -0.08
    ญ่
    -0.08
    -atụ
    -0.08
     sageli
    -0.08
     Percent
    -0.08
    (values
    -0.08
    POSITIVE LOGITS
     dynamics
    0.13
     motion
    0.13
     motions
    0.12
     geometry
    0.11
     distance
    0.11
    motion
    0.11
     movement
    0.11
     mouvement
    0.10
     behavior
    0.10
     displacement
    0.10
    Activations Density 0.003%

    No Known Activations