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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1288
    Prev
    Next
    INDEX
    Explanations

    io

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LGBT
    -0.09
     gay
    -0.08
    INUX
    -0.08
     torn
    -0.08
    /<?
    -0.08
    ;"><?
    -0.08
    uls
    -0.08
     homosexual
    -0.08
    'Brien
    -0.08
    引
    -0.07
    POSITIVE LOGITS
     Dataset
    0.08
    ieke
    0.08
     simpel
    0.08
     dívida
    0.08
    .Dataset
    0.08
    Vest
    0.08
    NYSE
    0.08
    0.07
     قات
    0.07
     essentieel
    0.07
    Activations Density 0.000%
    No Known Activations