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. 111626
    Prev
    Next
    INDEX
    Explanations

    work

    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
    ρι
    -0.07
     digs
    -0.07
     grounds
    -0.07
    Tube
    -0.07
     numer
    -0.07
     digging
    -0.07
    Seriously
    -0.07
     ومع
    -0.06
    Trademark
    -0.06
     λεπ
    -0.06
    POSITIVE LOGITS
    habit
    0.09
     bol
    0.08
    /stretch
    0.08
    реп
    0.08
    stro
    0.08
     pomen
    0.08
     menget
    0.08
     knit
    0.08
    сты
    0.08
     gevolg
    0.08
    Activations Density 0.010%

    No Known Activations