© 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. 18787
    Prev
    Next
    INDEX
    Explanations

    Beautiful Soup objects

    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
    onus
    -0.08
     garantiert
    -0.08
    asit
    -0.08
     sorgt
    -0.07
    .Autowired
    -0.07
    Libraries
    -0.07
    @index
    -0.07
    Growing
    -0.07
     guarantees
    -0.07
    partner
    -0.07
    POSITIVE LOGITS
     sélectionner
    0.15
     sélection
    0.15
     selecionar
    0.15
     seleccionar
    0.14
     seleção
    0.13
    .select
    0.13
    _selector
    0.13
     انتخاب
    0.13
     নির্বাচন
    0.13
     selección
    0.13
    Activations Density 0.001%

    No Known Activations