Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43040
    Prev
    Next
    INDEX
    Explanations

    **

    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
     یې
    -0.08
     misleading
    -0.08
     فإن
    -0.07
     neglig
    -0.07
     játék
    -0.07
     rato
    -0.07
     dann
    -0.07
    annya
    -0.07
     ardu
    -0.07
    rochen
    -0.07
    POSITIVE LOGITS
     aka
    0.10
    stemming
    0.08
    ()
    0.08
    (This
    0.08
    [^
    0.07
    (Vue
    0.07
    aka
    0.07
    �
    0.07
     cornerstone
    0.07
     เช่น
    0.07
    Activations Density 0.091%

    No Known Activations