© 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. 19-RESID-POST-AA
    11. 18864
    Prev
    Next
    INDEX
    Explanations

    :#

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ୟ
    -0.08
     necessary
    -0.08
     near
    -0.08
     specific
    -0.07
     veh
    -0.07
    IL
    -0.07
     \"
    -0.07
     کس
    -0.07
     compared
    -0.07
    ிய
    -0.07
    POSITIVE LOGITS
     كبيرة
    0.08
    =&
    0.08
    ,size
    0.08
    gaa
    0.08
    =size
    0.08
    005
    0.08
     riscos
    0.08
    006
    0.08
    :ring
    0.08
    größe
    0.08
    Activations Density 0.000%

    No Known Activations