© 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. 96345
    Prev
    Next
    INDEX
    Explanations

    distrib

    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
    zor
    -0.08
    quel
    -0.08
    զ
    -0.08
     يه
    -0.08
    Ber
    -0.08
     thousand
    -0.08
     beraten
    -0.07
    z
    -0.07
    cemic
    -0.07
    کرات
    -0.07
    POSITIVE LOGITS
    uidor
    0.15
    uciones
    0.12
    uid
    0.12
    ucional
    0.11
    uições
    0.11
    uzione
    0.10
    uib
    0.10
    ución
    0.10
    uidos
    0.10
    uscht
    0.10
    Activations Density 0.002%

    No Known Activations