© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 102509
    Prev
    Next
    INDEX
    Explanations

    Bot instructions

    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
     छैन
    -0.09
     இல்லை
    -0.09
     keine
    -0.08
     dikenal
    -0.08
    ちなみに
    -0.08
     లేదు
    -0.08
     먼저
    -0.08
    まず
    -0.08
     Keine
    -0.08
     nincs
    -0.08
    POSITIVE LOGITS
    以上
    0.16
    These
    0.13
     these
    0.13
    Таким
    0.13
    Overall
    0.12
     These
    0.12
     all
    0.12
    这些
    0.12
     overall
    0.12
     combine
    0.12
    Activations Density 0.087%

    No Known Activations