© 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. 70202
    Prev
    Next
    INDEX
    Explanations

    G-type stars

    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
     vlan
    -0.10
     VLAN
    -0.08
     лап
    -0.08
    ldap
    -0.08
     kugirango
    -0.08
     Compress
    -0.08
    ęg
    -0.08
     criminals
    -0.08
    穿
    -0.08
     holders
    -0.08
    POSITIVE LOGITS
     Earth's
    0.12
     comparable
    0.12
     مشابه
    0.11
    Comparable
    0.10
     resembling
    0.10
     mim
    0.10
     solar
    0.10
     semelhante
    0.09
     Mediterranean
    0.09
     similarities
    0.09
    Activations Density 0.007%

    No Known Activations