© 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. 7-RESID-POST-AA
    11. 1284
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uner
    -0.09
    েরা
    -0.08
    Cuál
    -0.07
    areg
    -0.07
    Biz
    -0.07
     sac
    -0.07
     springs
    -0.07
    堵
    -0.07
    Rt
    -0.07
    Weekend
    -0.07
    POSITIVE LOGITS
     usefulness
    0.09
     richness
    0.09
     سرعة
    0.09
     количество
    0.08
     смысл
    0.08
     сложности
    0.08
     wording
    0.08
     openness
    0.08
     snelheid
    0.08
     duración
    0.08
    Activations Density 0.064%

    No Known Activations