© 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. 45770
    Prev
    Next
    INDEX
    Explanations

    Order of operations

    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
     islands
    -0.08
    .dark
    -0.08
    DW
    -0.08
     Porsche
    -0.08
    'appar
    -0.08
     classement
    -0.08
    .AP
    -0.08
     schaut
    -0.07
     landmarks
    -0.07
     Warwick
    -0.07
    POSITIVE LOGITS
     signaling
    0.10
     linear
    0.08
    icates
    0.08
    ivatives
    0.08
     signalling
    0.08
     Linear
    0.08
    icate
    0.07
    iting
    0.07
     લગ્ન
    0.07
    _MINUS
    0.07
    Activations Density 0.001%

    No Known Activations