Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19358
    Prev
    Next
    INDEX
    Explanations

    simultaneous

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಕೆ
    -0.08
    单
    -0.07
    界
    -0.07
     �
    -0.07
     suddenly
    -0.07
    ingle
    -0.07
    liu
    -0.07
    teil
    -0.07
    নত
    -0.07
     Vander
    -0.07
    POSITIVE LOGITS
    -sama
    0.17
    aneously
    0.14
    aneous
    0.12
    aneamente
    0.10
     нескольких
    0.10
     നടക്കുന്ന
    0.09
    varande
    0.09
    anément
    0.09
     జరిగ
    0.08
    -साथ
    0.08
    Activations Density 0.016%

    No Known Activations