© 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. 49512
    Prev
    Next
    INDEX
    Explanations

    say 627

    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
     Bilbao
    -0.09
     Seattle
    -0.09
    _PC
    -0.09
    .b
    -0.08
    _pc
    -0.08
     बाक
    -0.08
    Seattle
    -0.08
    Bluetooth
    -0.08
     Welch
    -0.08
    Incl
    -0.08
    POSITIVE LOGITS
     Springfield
    0.11
     Sang
    0.10
     IL
    0.08
     Государ
    0.08
    одерж
    0.08
    627
    0.08
     Mak
    0.08
     Ma
    0.08
     villages
    0.08
     Ма
    0.08
    Activations Density 0.002%

    No Known Activations