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. 111647
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    phasis
    -0.08
     subdiv
    -0.08
     FUND
    -0.08
    phas
    -0.08
    基金
    -0.08
    íss
    -0.08
     Mandel
    -0.08
     chwil
    -0.08
     benefiting
    -0.07
     indrindra
    -0.07
    POSITIVE LOGITS
    чес
    0.09
     Tried
    0.08
    ено
    0.08
     Weird
    0.08
    너
    0.07
    еден
    0.07
    ена
    0.07
     tenté
    0.07
     tentou
    0.07
    requested
    0.07
    Activations Density 0.018%

    No Known Activations