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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 96903
    Prev
    Next
    INDEX
    Explanations

    tre

    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
    klar
    -0.08
     മുതല്
    -0.08
     koul
    -0.08
     يحتوي
    -0.08
    itario
    -0.08
    šti
    -0.08
    (freq
    -0.07
     wire
    -0.07
     freq
    -0.07
     kang
    -0.07
    POSITIVE LOGITS
    ceau
    0.09
    .cut
    0.09
    cut
    0.08
    ઈ
    0.08
     aps
    0.08
    íma
    0.08
     Series
    0.08
     Yen
    0.07
    Cut
    0.07
    ией
    0.07
    Activations Density 0.000%

    No Known Activations