© 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. 872
    Prev
    Next
    INDEX
    Explanations

    literal or literally

    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
    _definition
    -0.09
     egentlig
    -0.08
    _sessions
    -0.08
    _weapon
    -0.08
    /Game
    -0.08
     wzgl
    -0.08
     Rioja
    -0.08
    _GAME
    -0.08
    _ylim
    -0.08
    _game
    -0.08
    POSITIVE LOGITS
    固定
    0.12
     literal
    0.10
     fixed
    0.10
    fixed
    0.09
    literal
    0.09
    串
    0.09
     específicos
    0.09
    匹
    0.08
     Fixed
    0.08
    �
    0.08
    Activations Density 0.009%

    No Known Activations