© 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. 44784
    Prev
    Next
    INDEX
    Explanations

    dashes

    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
    CAT
    -0.09
    雄
    -0.08
     Sham
    -0.08
     pacing
    -0.08
    nand
    -0.07
     DD
    -0.07
     CAT
    -0.07
    nm
    -0.07
    ので
    -0.07
    點
    -0.07
    POSITIVE LOGITS
    ’industrie
    0.08
     चिकित
    0.08
     médic
    0.07
    'industrie
    0.07
     industr
    0.07
     শিল্প
    0.07
    .Maximum
    0.07
     ‘
    0.07
     grundleg
    0.07
     adhesives
    0.07
    Activations Density 0.002%

    No Known Activations