© 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. 64926
    Prev
    Next
    INDEX
    Explanations

    brackets/quotes

    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
     reinforced
    -0.08
     dug
    -0.08
    inel
    -0.08
     Reid
    -0.07
     hardcover
    -0.07
    ROUGH
    -0.07
    verket
    -0.07
    吞
    -0.07
    STRU
    -0.07
    Tele
    -0.07
    POSITIVE LOGITS
     injected
    0.09
     Helpful
    0.09
     Inject
    0.09
    jected
    0.09
    Useful
    0.08
     prepares
    0.08
    -bs
    0.08
    .locals
    0.07
    @Web
    0.07
     جاه
    0.07
    Activations Density 0.003%

    No Known Activations