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. 29861
    Prev
    Next
    INDEX
    Explanations

    they'd

    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
     Turbo
    -0.08
     fossils
    -0.08
     bes
    -0.07
     mà
    -0.07
    Tur
    -0.07
     OLD
    -0.07
    spiel
    -0.07
     giz
    -0.07
    обходим
    -0.07
     Butt
    -0.07
    POSITIVE LOGITS
     अश
    0.09
    ressa
    0.08
     interessiert
    0.08
     Hon
    0.08
     Alexis
    0.07
     strongly
    0.07
     seren
    0.07
     ngaj
    0.07
     المه
    0.07
     kunna
    0.07
    Activations Density 0.023%

    No Known Activations