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. 349
    Prev
    Next
    INDEX
    Explanations

    None

    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
    'autre
    -0.09
    Jn
    -0.08
    velopment
    -0.08
    情况下
    -0.07
    ensis
    -0.07
     Stephen
    -0.07
     মূল্য
    -0.07
    Avail
    -0.07
     Minerals
    -0.07
     Sam
    -0.07
    POSITIVE LOGITS
     (**
    0.07
     (*
    0.07
    (By
    0.07
    ("[
    0.07
     Select
    0.07
    (select
    0.07
     joins
    0.07
     informeren
    0.07
    [V
    0.07
     nort
    0.07
    Activations Density 0.002%

    No Known Activations