© 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. 3-RESID-POST-AA
    11. 1324
    Prev
    Next
    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bef
    -0.08
     ane
    -0.08
     εί
    -0.08
     sắc
    -0.08
     Ran
    -0.08
     dude
    -0.08
     Bieber
    -0.08
     Traders
    -0.08
    चा
    -0.08
     வாய
    -0.07
    POSITIVE LOGITS
    �
    0.08
    ET
    0.08
     fo
    0.08
    -PC
    0.08
     clo
    0.07
    anze
    0.07
     ethn
    0.07
    矿
    0.07
    保障
    0.07
     meas
    0.07
    Activations Density 0.002%

    No Known Activations