© 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. 148
    Prev
    Next
    INDEX
    Explanations

    allow/value

    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
     Planung
    -0.09
    /book
    -0.09
     Geburtstag
    -0.09
    (boost
    -0.09
    Serde
    -0.09
     Maha
    -0.08
    كلة
    -0.08
    Her
    -0.08
     Geburt
    -0.08
    (kind
    -0.08
    POSITIVE LOGITS
     ced
    0.08
     cols
    0.08
     columns
    0.07
     ф
    0.07
     template
    0.07
     зр
    0.07
     कोर्ट
    0.07
    cols
    0.07
     freeing
    0.07
    tabla
    0.07
    Activations Density 0.001%

    No Known Activations