© 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. 44893
    Prev
    Next
    INDEX
    Explanations

    X

    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
     obviously
    -0.08
     dividing
    -0.07
     phr
    -0.07
     nele
    -0.07
     divisible
    -0.07
     sod
    -0.07
     digital
    -0.07
    -digit
    -0.07
     numeric
    -0.07
     divide
    -0.07
    POSITIVE LOGITS
     관한
    0.08
    _Stream
    0.08
     arbitration
    0.08
    랍니다
    0.08
     Romano
    0.08
    Vz
    0.08
    ুগ
    0.08
     감사합니다
    0.08
     rebut
    0.08
     Arbitration
    0.08
    Activations Density 0.786%

    No Known Activations