© 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. 8086
    Prev
    Next
    INDEX
    Explanations

    word roots

    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
    _private
    -0.08
    ولي
    -0.07
    _SECRET
    -0.07
    တွ
    -0.07
    (sorted
    -0.07
     Secret
    -0.07
     meetings
    -0.07
    เหนือ
    -0.07
    _transfer
    -0.07
    #region
    -0.07
    POSITIVE LOGITS
     raíces
    0.14
     raí
    0.12
     raíz
    0.12
    -root
    0.11
     roots
    0.11
     raiz
    0.10
     Roots
    0.10
    植
    0.10
     grammatical
    0.10
     root
    0.10
    Activations Density 0.017%

    No Known Activations