© 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. 11-RESID-POST-AA
    11. 95304
    Prev
    Next
    INDEX
    Explanations

    Decoder

    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
     trafik
    -0.08
    .hash
    -0.08
     Tooth
    -0.08
     JText
    -0.07
     jungle
    -0.07
     textures
    -0.07
    Nj
    -0.07
    igneur
    -0.07
     necklaces
    -0.07
    ensity
    -0.07
    POSITIVE LOGITS
     lir
    0.08
    pand
    0.08
    0.07
    -peer
    0.07
     वास्त
    0.07
    Lyrics
    0.07
    _states
    0.07
    Architect
    0.07
    erli
    0.07
    لیک
    0.07
    Activations Density 0.001%
    No Known Activations