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. 8871
    Prev
    Next
    INDEX
    Explanations

    3

    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
     Farr
    -0.09
     baw
    -0.08
    /general
    -0.08
     conjuntos
    -0.08
     ==>
    -0.08
     ਵਾਲ
    -0.07
    -age
    -0.07
    ใช
    -0.07
    벽
    -0.07
     Lam
    -0.07
    POSITIVE LOGITS
    .Scale
    0.08
     fiel
    0.07
     torn
    0.07
     rod
    0.07
     reck
    0.07
     considered
    0.07
     ভ
    0.07
     rods
    0.07
     Tg
    0.07
    ored
    0.07
    Activations Density 0.002%

    No Known Activations