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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19359
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Prezidenti
    -0.08
     descont
    -0.08
     vatandaş
    -0.08
     Respublikas
    -0.08
    ိဳ
    -0.07
    στημα
    -0.07
     Oromiyaa
    -0.07
    _builtin
    -0.07
    كار
    -0.07
    uman
    -0.07
    POSITIVE LOGITS
     grupo
    0.40
     समूह
    0.39
     groupe
    0.39
     group
    0.38
     گروه
    0.38
     gruppo
    0.37
     그룹
    0.37
     kelompok
    0.37
     Gruppe
    0.36
     nhóm
    0.36
    Activations Density 0.092%

    No Known Activations