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. 90283
    Prev
    Next
    INDEX
    Explanations

    compose

    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
     pathogens
    -0.09
     народ
    -0.08
    εια
    -0.08
     Vir
    -0.08
     বন্দ
    -0.07
     מרכז
    -0.07
     зол
    -0.07
     أمريكا
    -0.07
    իտ
    -0.07
     inic
    -0.07
    POSITIVE LOGITS
     PF
    0.09
     CIM
    0.08
    बर
    0.08
    Activation
    0.08
    PF
    0.08
     ।↵↵
    0.08
     Activation
    0.08
    activation
    0.08
    avera
    0.07
    scenario
    0.07
    Activations Density 0.001%

    No Known Activations