© 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. 23-RESID-POST-AA
    11. 51829
    Prev
    Next
    INDEX
    Explanations

    Bl

    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
     तेजी
    -0.10
    Noch
    -0.09
     bubbling
    -0.08
    rieren
    -0.08
     QUICK
    -0.08
     faim
    -0.08
     BALL
    -0.08
    Bush
    -0.08
     spotting
    -0.08
     THEORY
    -0.08
    POSITIVE LOGITS
    ender
    0.14
    azor
    0.11
    ENDER
    0.10
    ending
    0.10
    aze
    0.10
    urable
    0.10
    itable
    0.10
    enders
    0.10
    azelo
    0.09
    ibli
    0.09
    Activations Density 0.004%

    No Known Activations