© 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. 23-RESID-POST-AA
    11. 6406
    Prev
    Next
    INDEX
    Explanations

    The Office

    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
     SNS
    -0.09
     websocket
    -0.08
    GENERAL
    -0.08
    -0.08
     CHAT
    -0.08
    $route
    -0.08
     coro
    -0.08
     Rádio
    -0.08
    LEM
    -0.08
    _chat
    -0.07
    POSITIVE LOGITS
    ाक्ष
    0.09
     Toby
    0.09
     Creek
    0.09
    Ryan
    0.08
     Schr
    0.08
    Aw
    0.08
    Dw
    0.08
    Crist
    0.08
     Andy
    0.08
     Michael
    0.08
    Activations Density 0.004%

    No Known Activations