© 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. 224
    Prev
    Next
    INDEX
    Explanations

    Letter a

    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
    .Anal
    -0.08
     substance
    -0.07
    орк
    -0.07
    .Namespace
    -0.07
    eria
    -0.07
     tournée
    -0.07
    (Comment
    -0.07
     thu
    -0.07
     prudent
    -0.07
     Fiscal
    -0.07
    POSITIVE LOGITS
     AMOLED
    0.11
    AVL
    0.09
     cil
    0.09
    OLED
    0.08
    Jag
    0.08
     OLED
    0.08
    0.08
     JBL
    0.08
     volleyball
    0.08
     NBA
    0.08
    Activations Density 0.013%
    No Known Activations