© 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. 7947
    Prev
    Next
    INDEX
    Explanations

    comma and quotation

    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
    22
    -0.07
    ############################################################################
    -0.07
     shoulder
    -0.07
    ################################################################################
    -0.07
     ulcers
    -0.07
    #region
    -0.07
     �
    -0.07
    MAP
    -0.07
    (M
    -0.07
    (PR
    -0.07
    POSITIVE LOGITS
    毛
    0.08
     lå
    0.08
     hairy
    0.08
     Hiro
    0.08
     毛
    0.08
    -Unter
    0.08
     erlebt
    0.08
     الشركة
    0.08
     berichtet
    0.08
     raport
    0.08
    Activations Density 0.071%

    No Known Activations