© 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. 50336
    Prev
    Next
    INDEX
    Explanations

    Foreign textual standards

    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
    ,V
    -0.09
    cycl
    -0.08
     vô
    -0.07
     Kam
    -0.07
    atá
    -0.07
    Sus
    -0.07
     Endless
    -0.07
    sus
    -0.07
     Cycl
    -0.07
     Magdalena
    -0.07
    POSITIVE LOGITS
     unir
    0.08
    ivr
    0.08
    egen
    0.08
    =user
    0.08
     corre
    0.08
     muut
    0.08
     versus
    0.07
    pite
    0.07
     kullanıcı
    0.07
    夫
    0.07
    Activations Density 0.000%

    No Known Activations