© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 99796
    Prev
    Next
    INDEX
    Explanations

    biolog

    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
     plank
    -0.09
     horny
    -0.09
     plum
    -0.08
     distracted
    -0.08
     Dund
    -0.08
     conscience
    -0.08
     cous
    -0.08
    pluck
    -0.08
     прист
    -0.08
     jeunesse
    -0.08
    POSITIVE LOGITS
     antibody
    0.08
    _encoder
    0.08
    otherapeut
    0.08
    _ENCOD
    0.08
    .encode
    0.08
     encoder
    0.07
    	b
    0.07
     antibodies
    0.07
    (z
    0.07
     বড়
    0.07
    Activations Density 0.009%

    No Known Activations