© 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. 19-RESID-POST-AA
    11. 103175
    Prev
    Next
    INDEX
    Explanations

    researchers and community

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unforgettable
    -0.09
    forgettable
    -0.08
     autobiography
    -0.08
    皇
    -0.08
     છોડ
    -0.08
     Emperor
    -0.08
    収納
    -0.08
     Président
    -0.07
     Certain
    -0.07
    ақыт
    -0.07
    POSITIVE LOGITS
     developers
    0.16
     researchers
    0.16
     community
    0.16
     pesquisadores
    0.15
    Researchers
    0.15
    社区
    0.15
     समुदाय
    0.14
     komunit
    0.14
     Researchers
    0.14
     comunidade
    0.14
    Activations Density 0.024%

    No Known Activations