© 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. 29569
    Prev
    Next
    INDEX
    Explanations

    day

    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
    amb
    -0.07
    Enh
    -0.07
     enhancing
    -0.07
    增强
    -0.07
    Instance
    -0.07
    .'
    -0.07
     μετα
    -0.07
     enhancements
    -0.07
    Bt
    -0.07
     --->
    -0.06
    POSITIVE LOGITS
     herinner
    0.10
    _wall
    0.09
     പ്രസിഡ
    0.09
     Vorsch
    0.08
     అధ్యక్ష
    0.08
    utsi
    0.08
     herkes
    0.08
     öffnen
    0.08
     wł
    0.08
     najle
    0.08
    Activations Density 0.000%

    No Known Activations