© 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. 54619
    Prev
    Next
    INDEX
    Explanations

    Code definitions

    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
     instinct
    -0.10
    _between
    -0.08
     instincts
    -0.08
    _throw
    -0.08
    ostics
    -0.07
     familiares
    -0.07
    07
    -0.07
     shoulder
    -0.07
     familiar
    -0.07
     objectively
    -0.07
    POSITIVE LOGITS
     babel
    0.10
     `"
    0.10
     Babel
    0.09
     stanza
    0.09
     khóa
    0.08
     Specifies
    0.08
     specifying
    0.08
    0.08
    .include
    0.08
     microphone
    0.08
    Activations Density 0.013%
    No Known Activations