© 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 EvalsExportsinterp-engineNEWAPI 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. 110626
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     Oromoo
    -0.10
     međunar
    -0.08
     Soomaaliyeed
    -0.08
    ๆ
    -0.08
    _offsets
    -0.08
     Europas
    -0.08
    ną
    -0.08
    -resistant
    -0.07
    iance
    -0.07
     världen
    -0.07
    POSITIVE LOGITS
    (the
    0.08
    करण
    0.08
     qualit
    0.08
    ppes
    0.07
    _CAP
    0.07
    .xlabel
    0.07
     controll
    0.07
     generals
    0.07
    (case
    0.07
    azini
    0.07
    Activations Density 0.050%

    No Known Activations