© 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. 48217
    Prev
    Next
    INDEX
    Explanations

    pre

    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
     J
    -0.09
     zit
    -0.08
     zeros
    -0.08
    J
    -0.08
     fa
    -0.07
     academ
    -0.07
    ోజ
    -0.07
     provisions
    -0.07
     облег
    -0.07
    Zeros
    -0.07
    POSITIVE LOGITS
    header
    0.10
    handler
    0.09
    sensor
    0.09
     Erin
    0.09
     Ernesto
    0.08
    эн
    0.08
     कर्मचारी
    0.08
     engr
    0.08
    主任
    0.08
    -header
    0.08
    Activations Density 0.001%

    No Known Activations