© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111198
    Prev
    Next
    INDEX
    Explanations

    says advertised

    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
     económico
    -0.08
     ఈ
    -0.08
     that'll
    -0.08
     cev
    -0.08
     ovoj
    -0.08
     ilimit
    -0.08
    -нибудь
    -0.08
     economia
    -0.07
     profunda
    -0.07
     sve
    -0.07
    POSITIVE LOGITS
     claimed
    0.12
     stated
    0.11
     advertised
    0.11
    宣传
    0.10
     marketed
    0.10
     vorgesehen
    0.09
     behaupt
    0.09
     intends
    0.09
     intended
    0.09
     দাব
    0.09
    Activations Density 0.034%

    No Known Activations