© 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. 110396
    Prev
    Next
    INDEX
    Explanations

    character

    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
     recessed
    -0.09
    億元
    -0.09
     hypocrisy
    -0.09
    .Remote
    -0.09
     rumored
    -0.09
    解除
    -0.09
     aron
    -0.09
     miliyoni
    -0.08
     CALLBACK
    -0.08
     nodra
    -0.08
    POSITIVE LOGITS
     alphabet
    0.09
    alphabet
    0.09
     tokenize
    0.08
     alfabet
    0.08
    jit
    0.08
     treating
    0.08
     ingest
    0.08
    phabet
    0.08
    Alphabet
    0.08
    .pkl
    0.08
    Activations Density 0.006%

    No Known Activations