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. 78627
    Prev
    Next
    INDEX
    Explanations

    pg

    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
    ocomplete
    -0.08
     поколения
    -0.08
     разработки
    -0.08
    avorable
    -0.07
     всего
    -0.07
     hora
    -0.07
     hig
    -0.07
    GEST
    -0.07
     പല
    -0.07
    ಉ
    -0.07
    POSITIVE LOGITS
     Bluff
    0.07
     healthy
    0.07
     tru
    0.07
     coffees
    0.07
     alm
    0.07
     Mustang
    0.07
     blonde
    0.07
     Murray
    0.07
     পড়
    0.06
     Amazing
    0.06
    Activations Density 0.003%

    No Known Activations