© 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. 11-RESID-POST-AA
    11. 78202
    Prev
    Next
    INDEX
    Explanations

    property

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Traf
    -0.08
    NSBundle
    -0.08
     assessing
    -0.08
     заинтерес
    -0.07
    .product
    -0.07
     voeren
    -0.07
    və
    -0.07
     érde
    -0.07
     Feld
    -0.07
    .credit
    -0.07
    POSITIVE LOGITS
     symmetrical
    0.09
     symmetry
    0.09
     doubling
    0.09
    规律
    0.08
     नियम
    0.08
     cong
    0.08
    _rules
    0.08
     Rules
    0.08
    规则
    0.08
    Rewrite
    0.08
    Activations Density 0.032%

    No Known Activations