© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 49650
    Prev
    Next
    INDEX
    Explanations

    remote

    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
     Haarlem
    -0.11
     città
    -0.11
     Cities
    -0.10
     city
    -0.10
     urbano
    -0.10
     Amsterdam
    -0.10
    _city
    -0.10
     Urban
    -0.10
     City
    -0.10
    東京都
    -0.10
    POSITIVE LOGITS
     remote
    0.23
    remote
    0.19
     remoto
    0.19
     mountainous
    0.18
    Remote
    0.17
     isolated
    0.17
    (remote
    0.17
     border
    0.16
     Remote
    0.16
    .remote
    0.16
    Activations Density 0.036%

    No Known Activations