© 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. 23-RESID-POST-AA
    11. 96300
    Prev
    Next
    INDEX
    Explanations

    co

    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
    утат
    -0.09
    اسة
    -0.09
     formas
    -0.09
    ancies
    -0.08
    cesse
    -0.08
    라고
    -0.08
    ANCES
    -0.08
     maneiras
    -0.08
    CEF
    -0.08
     quarterback
    -0.08
    POSITIVE LOGITS
    zy
    0.17
    zych
    0.12
    zył
    0.11
    zyn
    0.11
    ZY
    0.11
     cozy
    0.10
    zyc
    0.10
    zyka
    0.10
     Cozy
    0.09
    zyk
    0.09
    Activations Density 0.001%

    No Known Activations