© 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. 3-RESID-POST-AA
    11. 2597
    Prev
    Next
    INDEX
    Explanations

    Material

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     emperor
    -0.09
     Emperor
    -0.09
     kraju
    -0.08
     шар
    -0.08
    175
    -0.08
    taus
    -0.08
    береж
    -0.08
     vik
    -0.08
    skar
    -0.08
    ittest
    -0.08
    POSITIVE LOGITS
    .all
    0.08
    le
    0.07
    (z
    0.07
    Circ
    0.07
     hole
    0.07
     atribu
    0.07
     chord
    0.07
     letra
    0.07
     prote
    0.07
    ೊಂದಿಗೆ
    0.07
    Activations Density 0.001%

    No Known Activations