© 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. 103354
    Prev
    Next
    INDEX
    Explanations

    Touching or adjacent

    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
    乱码
    -0.09
     vielseit
    -0.09
     lyrics
    -0.08
     indictment
    -0.08
     XPath
    -0.08
     роль
    -0.08
     screenplay
    -0.08
    _any
    -0.08
     Any
    -0.08
    .role
    -0.08
    POSITIVE LOGITS
     externally
    0.17
     gegense
    0.14
     neighboring
    0.14
     touching
    0.14
     birbir
    0.14
     서로
    0.14
     mutual
    0.13
     external
    0.13
     adjacent
    0.13
    External
    0.13
    Activations Density 0.018%

    No Known Activations