© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 5402
    Prev
    Next
    INDEX
    Explanations

    single quote

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ،
    -0.08
    ോഷ്യ
    -0.08
     —
    -0.08
     вниз
    -0.08
      
    -0.08
     Shay
    -0.08
     pats
    -0.08
    ошт
    -0.08
    شت
    -0.08
    atically
    -0.08
    POSITIVE LOGITS
    xdd
    0.13
    xce
    0.13
    xee
    0.12
    xde
    0.12
    xcd
    0.12
    xae
    0.11
    xbb
    0.11
    xac
    0.11
    xea
    0.11
    xdc
    0.11
    Activations Density 0.003%

    No Known Activations