© 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. 11-RESID-POST-AA
    11. 129507
    Prev
    Next
    INDEX
    Explanations

    So

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ..\
    -0.08
    まだ
    -0.08
     ڇڏيو
    -0.08
     dye
    -0.08
     atm
    -0.08
     Place
    -0.08
    бии
    -0.08
     Seal
    -0.07
    بيا
    -0.07
    px
    -0.07
    POSITIVE LOGITS
    Import
    0.09
     determining
    0.08
     arbitrary
    0.08
    -testing
    0.08
    >/<
    0.08
     inequ
    0.08
     governed
    0.08
     determinants
    0.08
    Factors
    0.08
     എന്നാണ്
    0.08
    Activations Density 0.065%

    No Known Activations