© 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. 18867
    Prev
    Next
    INDEX
    Explanations

    Hindi grammatical markers

    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
    orium
    -0.09
    ogene
    -0.09
     хийх
    -0.09
    нення
    -0.08
    onia
    -0.08
    ithre
    -0.08
    icks
    -0.07
    otherwise
    -0.07
     qilish
    -0.07
    ować
    -0.07
    POSITIVE LOGITS
     वालों
    0.14
     वाला
    0.13
     والوں
    0.13
     वाली
    0.13
     والے
    0.12
     वाले
    0.12
    छन्
    0.12
     والی
    0.11
     के
    0.11
     على
    0.11
    Activations Density 0.001%

    No Known Activations