© 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. 1509
    Prev
    Next
    INDEX
    Explanations

    var

    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
     programmable
    -0.09
    ය
    -0.08
    UK
    -0.08
    Gl
    -0.08
     Gl
    -0.08
     anex
    -0.07
     Vigil
    -0.07
     Glide
    -0.07
     sheet
    -0.07
     defendants
    -0.07
    POSITIVE LOGITS
     diamant
    0.08
     oer
    0.08
     frère
    0.08
    -country
    0.07
    _country
    0.07
     ç
    0.07
     skatt
    0.07
     Caj
    0.07
     father's
    0.07
     muh
    0.07
    Activations Density 0.000%

    No Known Activations