© 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. 70310
    Prev
    Next
    INDEX
    Explanations

    Pro

    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
    地产
    -0.08
     lul
    -0.07
     bloqueo
    -0.07
     reforms
    -0.07
     botan
    -0.07
    allist
    -0.07
     Pflanzen
    -0.07
    经营
    -0.07
     probate
    -0.07
    ewn
    -0.07
    POSITIVE LOGITS
    bodaeth
    0.08
     footage
    0.08
     Во
    0.08
     exam
    0.08
     ubiquitous
    0.08
     eval
    0.07
     vlog
    0.07
     വീഡിയോ
    0.07
    -esque
    0.07
    (eval
    0.07
    Activations Density 0.001%

    No Known Activations