© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7582
    Prev
    Next
    INDEX
    Explanations

    Qualifying or negating statements

    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
     görev
    -0.08
     ggf
    -0.08
     Scho
    -0.08
     reduziert
    -0.08
     zmanjš
    -0.07
    gaard
    -0.07
     Don
    -0.07
     கூட
    -0.07
     krem
    -0.07
    itiv
    -0.07
    POSITIVE LOGITS
    という
    0.10
    」という
    0.09
    이라는
    0.08
     ন
    0.08
     quelque
    0.07
     nějak
    0.07
     అనే
    0.07
     деген
    0.07
    ಜ
    0.07
    益
    0.07
    Activations Density 0.418%

    No Known Activations