© 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. 19-RESID-POST-AA
    11. 19129
    Prev
    Next
    INDEX
    Explanations

    ring

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     little
    -0.08
    🏼
    -0.08
     playful
    -0.08
     рел
    -0.07
    ият
    -0.07
    🏻
    -0.07
    олго
    -0.07
     재미
    -0.07
     удовольствие
    -0.07
    GING
    -0.07
    POSITIVE LOGITS
    -shaped
    0.13
    ाकार
    0.12
    vaart
    0.12
    -around
    0.12
    worm
    0.11
    around
    0.11
    worms
    0.11
    maat
    0.10
    Around
    0.10
    াকার
    0.10
    Activations Density 0.041%

    No Known Activations