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. 65262
    Prev
    Next
    INDEX
    Explanations

    anti

    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
    òa
    -0.09
    olen
    -0.08
     altos
    -0.08
     afge
    -0.08
     hinein
    -0.07
    ുകയാണ്
    -0.07
     seg
    -0.07
    BEGIN
    -0.07
    _shell
    -0.07
    oline
    -0.07
    POSITIVE LOGITS
     antibody
    0.10
     antibodies
    0.10
     fibers
    0.09
     fibres
    0.08
     thread
    0.08
     ткан
    0.08
    이버
    0.08
    екция
    0.08
     entraîner
    0.08
     postcard
    0.08
    Activations Density 0.005%

    No Known Activations