© 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. 19-RESID-POST-AA
    11. 102697
    Prev
    Next
    INDEX
    Explanations

    say "-digit"

    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
     socials
    -0.10
     miks
    -0.10
     ibi
    -0.09
     Africans
    -0.09
     kuwo
    -0.09
     combos
    -0.09
    adorias
    -0.08
     rambut
    -0.08
     coro
    -0.08
     hala
    -0.08
    POSITIVE LOGITS
    ­
    0.15
    −
    0.14
    ­­
    0.14
    ‐
    0.14
    ‑
    0.14
    \-
    0.13
    –
    0.13
    －
    0.13
    -​
    0.13
     ­
    0.13
    Activations Density 0.013%

    No Known Activations