© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49438
    Prev
    Next
    INDEX
    Explanations

    ond

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ണ്ഡ
    -0.10
     soyez
    -0.09
     awer
    -0.09
     adunay
    -0.09
     اقتصادي
    -0.09
     mett
    -0.09
    clared
    -0.09
    legd
    -0.09
     nyuma
    -0.09
     kasance
    -0.09
    POSITIVE LOGITS
    isi
    0.13
    resi
    0.12
    si
    0.12
    esi
    0.12
    ensi
    0.11
    inisi
    0.11
    firmasi
    0.11
    uksi
    0.10
    usi
    0.10
    ansi
    0.10
    Activations Density 0.004%

    No Known Activations