© 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. 47242
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
     uy
    -0.08
    ONLY
    -0.08
    壮
    -0.08
     suje
    -0.07
     mulher
    -0.07
     ingresso
    -0.07
     lalaki
    -0.07
    Uy
    -0.07
    Additional
    -0.07
    _ONLY
    -0.07
    POSITIVE LOGITS
     �
    0.09
     😊
    0.09
    ครับ
    0.09
     вычис
    0.09
     hjälpa
    0.08
     خلاص
    0.08
     �
    0.08
     reasoning
    0.08
     workings
    0.08
    &apos
    0.08
    Activations Density 0.052%

    No Known Activations