© 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. 70393
    Prev
    Next
    INDEX
    Explanations

    ogram

    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
    ną
    -0.09
    iffany
    -0.08
     dew
    -0.08
    Scrolling
    -0.08
    下来
    -0.08
     scrolling
    -0.08
    Decrease
    -0.08
    enne
    -0.08
    slides
    -0.08
     Maus
    -0.08
    POSITIVE LOGITS
    (commands
    0.08
     We'd
    0.08
     bloqueo
    0.07
     beschäftigt
    0.07
    (Collections
    0.07
     Bloc
    0.07
    近年来
    0.07
     య
    0.07
    _commands
    0.07
     commands
    0.07
    Activations Density 0.001%

    No Known Activations