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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58789
    Prev
    Next
    INDEX
    Explanations

    title

    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
    ddi
    -0.08
     synt
    -0.08
     nyn
    -0.08
    fee
    -0.08
    chain
    -0.07
    ensional
    -0.07
     auparavant
    -0.07
    ന്ന്
    -0.07
    heur
    -0.07
    സി
    -0.07
    POSITIVE LOGITS
     Camel
    0.09
     majest
    0.08
    Camel
    0.08
     מתאים
    0.08
    탕
    0.08
     Sonoma
    0.08
    :title
    0.08
     Ceremony
    0.08
     progetto
    0.08
     Witch
    0.08
    Activations Density 0.004%

    No Known Activations