© 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. 44938
    Prev
    Next
    INDEX
    Explanations

    Auscultation

    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
     Anw
    -0.07
    iya
    -0.07
     notation
    -0.07
     status
    -0.07
    다는
    -0.07
     ми
    -0.07
     мер
    -0.07
    -0.07
     Administrator
    -0.07
     computing
    -0.07
    POSITIVE LOGITS
    曝
    0.09
    BEST
    0.08
    Ener
    0.08
    Kw
    0.08
     ಭಾಷ
    0.08
     plex
    0.08
    床
    0.08
     ekstrem
    0.08
     BEST
    0.08
     Elabor
    0.08
    Activations Density 0.002%
    No Known Activations