© 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. 96458
    Prev
    Next
    INDEX
    Explanations

    .

    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
    -inter
    -0.08
     q
    -0.08
     gr
    -0.08
     Inter
    -0.08
     Grace
    -0.07
    巻
    -0.07
     ગ્ર
    -0.07
     గ్ర
    -0.07
     gracia
    -0.07
     powin
    -0.07
    POSITIVE LOGITS
     logistics
    0.08
    <th
    0.08
     Das
    0.07
     հոգ
    0.07
    @Component
    0.07
     الدولي
    0.07
     ճանաչ
    0.07
     مها
    0.07
    host
    0.07
    _dims
    0.07
    Activations Density 0.013%

    No Known Activations