© 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. 11-RESID-POST-AA
    6. 75854
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Pal
    -0.08
    Combat
    -0.08
     million
    -0.08
    Millions
    -0.08
     laut
    -0.07
     CI
    -0.07
    CI
    -0.07
    SSR
    -0.07
     moderno
    -0.07
    Compatibility
    -0.07
    POSITIVE LOGITS
    เอียด
    0.09
    .constants
    0.09
     AMC
    0.08
     ausdr
    0.08
     fellow
    0.08
     mulig
    0.08
     yadda
    0.07
    his
    0.07
     erfaring
    0.07
     иц
    0.07
    Activations Density 0.028%

    No Known Activations