© 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. 15-RESID-POST-AA
    11. 16685
    Prev
    Next
    INDEX
    Explanations

    2

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    हन
    -0.08
     possam
    -0.07
     بالفعل
    -0.07
     rues
    -0.07
     rue
    -0.07
     atre
    -0.07
    /antlr
    -0.07
     errs
    -0.07
     Fuller
    -0.07
    ADM
    -0.07
    POSITIVE LOGITS
     yapıl
    0.09
     =
    0.09
    _eq
    0.08
     şekl
    0.08
     venir
    0.08
     solved
    0.08
     എന്നീ
    0.08
    ney
    0.08
    oso
    0.07
    ides
    0.07
    Activations Density 0.004%

    No Known Activations