© 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. 91542
    Prev
    Next
    INDEX
    Explanations

    Neptune

    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
     span
    -0.08
     ruler
    -0.08
     tjen
    -0.07
     '#'
    -0.07
     beginners
    -0.07
     ISR
    -0.07
     looming
    -0.07
     будущ
    -0.07
     feature
    -0.07
    fea
    -0.07
    POSITIVE LOGITS
     reparación
    0.09
     réparation
    0.09
    partner
    0.08
     Sham
    0.08
     modificación
    0.08
     Kata
    0.08
     remis
    0.08
     Diario
    0.08
     compagnon
    0.08
    izan
    0.08
    Activations Density 0.010%

    No Known Activations