© 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. 79032
    Prev
    Next
    INDEX
    Explanations

    SQL code

    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
    QRSTUVWXYZ
    -0.08
    <Edge
    -0.08
     strained
    -0.08
    すす
    -0.08
     eerlijk
    -0.08
     sunglasses
    -0.08
    hill
    -0.08
    139
    -0.08
     eighth
    -0.07
     nyl
    -0.07
    POSITIVE LOGITS
    DECLARE
    0.12
     VBA
    0.11
    	DECLARE
    0.10
     DECL
    0.09
     varchar
    0.08
     Fiscal
    0.08
     VARCHAR
    0.08
    .sql
    0.08
     declarar
    0.08
     선언
    0.08
    Activations Density 0.007%

    No Known Activations