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. 78595
    Prev
    Next
    INDEX
    Explanations

    version

    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
    ार्थ
    -0.09
     Plaint
    -0.08
     imposs
    -0.08
    라는
    -0.07
    overs
    -0.07
     confession
    -0.07
     inoc
    -0.07
     truthful
    -0.07
    弱
    -0.07
     Craig
    -0.07
    POSITIVE LOGITS
    是多少
    0.09
    -dependent
    0.09
     lama
    0.09
     tinggi
    0.08
     dependant
    0.08
     زیادی
    0.08
    (Window
    0.07
    ierung
    0.07
     Cosm
    0.07
     Vogue
    0.07
    Activations Density 0.009%

    No Known Activations