© 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. 21973
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    recursive
    -0.09
    ૧
    -0.08
    ૫
    -0.08
    ੧
    -0.08
    Indented
    -0.08
    فاءة
    -0.08
    ۾
    -0.08
    ע
    -0.08
    /path
    -0.08
    ೧
    -0.08
    POSITIVE LOGITS
     neutron
    0.16
    utron
    0.13
    ium
    0.10
    -rich
    0.10
    onium
    0.10
     nuclei
    0.10
     neut
    0.10
     cores
    0.09
     stars
    0.09
    ization
    0.09
    Activations Density 0.004%

    No Known Activations