© 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. 102630
    Prev
    Next
    INDEX
    Explanations

    faint

    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
     صغير
    -0.12
     קטן
    -0.10
     Small
    -0.09
     Verhältnis
    -0.09
     或
    -0.09
     ต่ำ
    -0.09
     ساده
    -0.09
     قليل
    -0.09
     دقیق
    -0.09
     moderately
    -0.09
    POSITIVE LOGITS
    est
    0.12
    ening
    0.11
    hearted
    0.11
    ness
    0.11
     shimmer
    0.09
    -hearted
    0.09
    ened
    0.09
     glow
    0.09
     smile
    0.09
     echo
    0.09
    Activations Density 0.005%

    No Known Activations